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

    Neuronpedia

    INDEX
    Explanations

    names of different people

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals involved in significant events or incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ±
    -0.79
    oshenko
    -0.79
     Crate
    -0.75
    rett
    -0.74
    ãĥ¯
    -0.71
    uments
    -0.71
    strate
    -0.70
    д
    -0.69
    ãĥ¥
    -0.69
    ATES
    -0.66
    POSITIVE LOGITS
     Wick
    0.92
    sein
    0.90
     Hutchinson
    0.84
     Hutch
    0.82
    row
    0.76
    urdue
    0.75
     plur
    0.74
    emb
    0.74
    cliffe
    0.73
    ness
    0.71
    Act Density 0.027%

    No Known Activations