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

    Neuronpedia

    INDEX
    Explanations

    words related to supernatural or mythical beings or beliefs

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    abouts
    -0.65
    jri
    -0.65
    lease
    -0.63
    isure
    -0.62
    kson
    -0.62
     Rough
    -0.62
    nce
    -0.61
    RAFT
    -0.59
    ills
    -0.59
    IGH
    -0.58
    POSITIVE LOGITS
    stration
    1.23
    strate
    1.01
    iac
    1.01
    ormal
    0.98
    esses
    0.89
    oid
    0.88
    ises
    0.85
    ciples
    0.83
    ising
    0.82
    atural
    0.80
    Act Density 0.079%

    No Known Activations