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

    Neuronpedia

    INDEX
    Explanations

    phrase structures involving the words "on" and "to"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.87
    脚注の使い方
    -0.84
     Carmichael
    -0.83
    newtheorem
    -0.79
    原始内容存档于
    -0.79
    liani
    -0.78
     Dij
    -0.70
    NewValue
    -0.70
    ี
    -0.69
     ITIS
    -0.68
    POSITIVE LOGITS
     Ong
    0.91
    Ong
    0.78
     Ons
    0.76
     ONS
    0.76
    ed
    0.74
     onBind
    0.73
     ON
    0.71
    isOn
    0.71
    Ons
    0.68
    setOn
    0.67
    Act Density 0.060%

    No Known Activations