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

    Neuronpedia

    INDEX
    Explanations

    the word "conf" followed by different suffixes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "confederation" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DAY
    -0.86
    senal
    -0.84
    hyde
    -0.83
    ï¸ı
    -0.73
    BALL
    -0.68
    Ô
    -0.66
    NING
    -0.66
    ngth
    -0.65
    manship
    -0.65
    matically
    -0.64
    POSITIVE LOGITS
    ederation
    1.15
    luence
    1.14
    eder
    1.07
    essional
    1.06
    usions
    1.02
    licted
    0.93
    etti
    0.92
    idences
    0.90
    eree
    0.89
    ining
    0.87
    Act Density 0.008%

    No Known Activations