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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating perception and changes in awareness or understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.02
    2:0.16
    3:0.07
    4:0.16
    5:0.08
    6:0.03
    7:0.02
    8:0.17
    9:0.07
    10:0.06
    11:0.02
    Negative Logits
    verages
    -1.38
    states
    -1.26
     vantage
    -1.19
    lihood
    -1.13
     extends
    -1.11
    lat
    -1.11
     buttocks
    -1.09
    sun
    -1.08
    pi
    -1.07
    lah
    -1.07
    POSITIVE LOGITS
    ALK
    1.49
     anew
    1.44
    OUND
    1.35
    EAR
    1.31
     Canaver
    1.30
    ODY
    1.29
    OOD
    1.24
    daq
    1.23
    RFC
    1.18
     hostilities
    1.18
    Act Density 0.024%

    No Known Activations