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

    Neuronpedia

    INDEX
    Explanations

    words associated with quality or ratings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    to
    -0.61
    ta
    -0.58
    li
    -0.55
    tampa
    -0.52
    liv
    -0.51
    ti
    -0.51
    te
    -0.50
    AutoField
    -0.49
    teen
    -0.49
    🏻
    -0.49
    POSITIVE LOGITS
    aaaa
    0.69
    aaaaaaaa
    0.67
    aaaaa
    0.63
    aaa
    0.60
    rea
    0.59
    aaaaaa
    0.59
    ceous
    0.59
    relli
    0.58
    re
    0.57
    bility
    0.57
    Act Density 0.661%

    No Known Activations