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

    Neuronpedia

    INDEX
    Explanations

    questions about the origin or source of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that inquire about origins or sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sav
    -0.75
    asio
    -0.64
    eatures
    -0.64
    iew
    -0.64
    ilt
    -0.64
    ilts
    -0.61
     Davidson
    -0.60
    bda
    -0.60
    cape
    -0.58
    roe
    -0.57
    POSITIVE LOGITS
     unst
    0.71
     from
    0.70
     FROM
    0.66
    From
    0.64
    owship
    0.64
     closest
    0.62
     From
    0.61
    ãĤ¼
    0.60
    oct
    0.60
    from
    0.59
    Act Density 0.024%

    No Known Activations