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

    Neuronpedia

    INDEX
    Explanations

    infinitive verbs, particularly indicating actions or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.12
    3:0.11
    4:0.04
    5:0.04
    6:0.12
    7:0.15
    8:0.04
    9:0.04
    10:0.09
    11:0.16
    Negative Logits
    aneously
    -1.49
    geoning
    -1.41
    astically
    -1.36
     awaits
    -1.36
     confessions
    -1.33
    urrencies
    -1.33
    aciously
    -1.30
     Scores
    -1.28
    ENGTH
    -1.25
     scores
    -1.24
    POSITIVE LOGITS
     anymore
    1.93
     bother
    1.62
     サーティワン
    1.56
     worry
    1.56
     condem
    1.51
    icer
    1.50
    ッド
    1.50
     exha
    1.46
     bothering
    1.42
     entirely
    1.41
    Act Density 0.011%

    No Known Activations