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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating frequency or repetition

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating frequency or universality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mire
    -0.65
    poke
    -0.64
    ubi
    -0.62
    omics
    -0.62
     Jedi
    -0.60
     Dod
    -0.60
    angelo
    -0.60
    clus
    -0.58
    ati
    -0.58
     Bard
    -0.58
    POSITIVE LOGITS
    hyde
    0.78
     imaginable
    0.72
    WAYS
    0.71
     consist
    0.68
    STD
    0.68
    xual
    0.66
     occupations
    0.64
     conceivable
    0.63
    ricular
    0.63
    body
    0.63
    Act Density 0.073%

    No Known Activations