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

    Neuronpedia

    INDEX
    Explanations

    single-letter detections located within a word

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of an empty or blank text segment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Angus
    -0.69
     Emerson
    -0.69
     appointments
    -0.67
     Allied
    -0.66
     Mellon
    -0.66
     Eag
    -0.65
     Borders
    -0.63
     Jagu
    -0.63
     Osh
    -0.62
     Clarkson
    -0.61
    POSITIVE LOGITS
    cess
    0.87
    sexual
    0.85
    ria
    0.85
    lex
    0.83
    vec
    0.83
    ird
    0.81
    lder
    0.81
     guest
    0.80
     ][
    0.80
    ctors
    0.75
    Act Density 0.053%

    No Known Activations