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

    Neuronpedia

    INDEX
    Explanations

    instances of affirmation or certainty in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.03
    2:0.10
    3:0.04
    4:0.05
    5:0.05
    6:0.18
    7:0.05
    8:0.10
    9:0.18
    10:0.03
    11:0.04
    Negative Logits
    三
    -3.95
     Samoa
    -3.87
     samurai
    -3.69
     Zoro
    -3.64
     fam
    -3.63
    obyl
    -3.63
    ゴン
    -3.55
    Alias
    -3.49
    ahime
    -3.43
     villagers
    -3.40
    POSITIVE LOGITS
     Steele
    10.94
    Ste
    6.48
    eele
    5.51
     Stein
    4.67
     Stone
    4.30
     Fusion
    3.98
     Transfer
    3.97
     Ste
    3.90
     Stef
    3.88
     Stellar
    3.86
    Act Density 0.001%

    No Known Activations