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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the apostrophe character in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vg
    -0.69
    enza
    -0.67
    sted
    -0.65
    ulhu
    -0.65
    mented
    -0.64
    asing
    -0.63
    fp
    -0.63
    Ļ½
    -0.63
    rador
    -0.63
     fert
    -0.61
    POSITIVE LOGITS
     own
    0.90
     penchant
    0.77
     intentions
    0.75
     throats
    0.74
     collective
    0.73
     brains
    0.72
     inaugural
    0.72
     accomplishments
    0.68
     frustrations
    0.68
     wives
    0.68
    Act Density 0.030%

    No Known Activations