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

    Neuronpedia

    INDEX
    Explanations

    terms related to social and emotional issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.03
    2:0.02
    3:0.09
    4:0.41
    5:0.06
    6:0.04
    7:0.02
    8:0.06
    9:0.10
    10:0.02
    11:0.02
    Negative Logits
    emphasis
    -2.84
    JP
    -2.63
    OPLE
    -2.47
    Figure
    -2.44
     Badge
    -2.42
    :[
    -2.36
     Mund
    -2.34
     Tee
    -2.31
    cu
    -2.27
     Quote
    -2.25
    POSITIVE LOGITS
    istical
    2.41
    kefeller
    2.38
    iera
    2.38
    ageddon
    2.22
    ufact
    2.19
    owl
    2.17
    estine
    2.17
    icho
    2.14
    leground
    2.14
    urned
    2.11
    Act Density 0.013%

    No Known Activations