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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to popular culture and entertainment industries

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character "ĺ" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     skelet
    -0.84
     mathemat
    -0.82
    matic
    -0.78
    matically
    -0.77
     pestic
    -0.76
    ulative
    -0.72
     incorpor
    -0.72
     horm
    -0.70
     scrut
    -0.69
     contrace
    -0.69
    POSITIVE LOGITS
    âĶĢâĶĢ
    0.92
    Ze
    0.77
    Hart
    0.77
    çľ
    0.74
    ï¸ı
    0.74
    fter
    0.73
    LV
    0.73
    è¡
    0.73
    orth
    0.73
    te
    0.71
    Act Density 0.062%

    No Known Activations