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

    Neuronpedia

    INDEX
    Explanations

    words related to endlessness, impossibility, or inescapable situations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to inexhaustibility or indefinability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hyde
    -0.92
    chens
    -0.76
    tsky
    -0.75
    culosis
    -0.74
     Remastered
    -0.72
    wagen
    -0.71
    anwhile
    -0.71
    mberg
    -0.69
     roofs
    -0.67
    steen
    -0.65
    POSITIVE LOGITS
    cus
    0.94
    cient
    0.93
    uitive
    0.93
    haust
    0.91
    uably
    0.90
    ences
    0.89
    urious
    0.88
    actly
    0.84
    pect
    0.83
    cept
    0.80
    Act Density 0.010%

    No Known Activations