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

    Neuronpedia

    INDEX
    Explanations

    references to research data and studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.09
    3:0.09
    4:0.11
    5:0.04
    6:0.06
    7:0.24
    8:0.05
    9:0.05
    10:0.08
    11:0.09
    Negative Logits
     Bundy
    -1.48
    cient
    -1.44
    teness
    -1.42
    �
    -1.41
    �
    -1.40
     Kov
    -1.40
     Amos
    -1.39
     Vish
    -1.38
    doms
    -1.35
    meat
    -1.35
    POSITIVE LOGITS
     recollection
    1.52
     authorization
    1.50
     sanction
    1.50
     encountering
    1.46
     predec
    1.45
    ↑
    1.44
     recol
    1.42
     completion
    1.39
     release
    1.38
     recomm
    1.38
    Act Density 0.001%

    No Known Activations