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

    Neuronpedia

    INDEX
    Explanations

    the conjunction "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.07
    2:0.08
    3:0.08
    4:0.08
    5:0.07
    6:0.08
    7:0.09
    8:0.08
    9:0.08
    10:0.09
    11:0.07
    Negative Logits
    ulhu
    -2.98
    plom
    -2.67
     Godzilla
    -2.63
     Lovecraft
    -2.60
    begin
    -2.53
    ô
    -2.52
     seiz
    -2.50
    bees
    -2.50
     Hitchcock
    -2.49
    FK
    -2.48
    POSITIVE LOGITS
     Rural
    3.41
     Scy
    2.96
     MI
    2.74
     Peninsula
    2.71
     Insp
    2.70
     Yar
    2.65
     Insight
    2.64
     Seb
    2.59
     Scotia
    2.58
    iku
    2.56
    Act Density 0.000%

    No Known Activations