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

    Neuronpedia

    INDEX
    Explanations

    names and titles of individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals or proper nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     FANT
    -0.78
     BEFORE
    -0.77
    Firstly
    -0.66
     ONE
    -0.66
     HERE
    -0.65
     CAN
    -0.65
     NEVER
    -0.65
    Tonight
    -0.63
    OVER
    -0.62
     TYPE
    -0.62
    POSITIVE LOGITS
     likewise
    0.83
    maxwell
    0.74
    bernatorial
    0.72
     langu
    0.71
    aeus
    0.68
    another
    0.67
     meanwhile
    0.67
     similarly
    0.66
    hemoth
    0.65
    yang
    0.63
    Act Density 0.432%

    No Known Activations