Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    technical and scientific information, particularly related to research, experiments, and data analysis

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    prepositions and words related to spatial orientation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.03
    2:0.16
    3:0.04
    4:0.20
    5:0.05
    6:0.02
    7:0.03
    8:0.16
    9:0.15
    10:0.05
    11:0.03
    Negative Logits
    SPONSORED
    -1.40
    TION
    -1.33
    cci
    -1.31
     Logged
    -1.21
    Cola
    -1.18
    ��
    -1.18
    FML
    -1.17
    Brew
    -1.15
     Mongo
    -1.15
     Stout
    -1.14
    POSITIVE LOGITS
    ゴン
    1.54
    itud
    1.51
     ana
    1.35
    phia
    1.34
     Brah
    1.34
    女
    1.31
     piety
    1.30
    ahime
    1.29
     wed
    1.26
    rawdownloadcloneembedreportprint
    1.25
    Act Density 0.006%

    No Known Activations