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

    Neuronpedia

    INDEX
    Explanations

    references to biological processes and phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Hack
    -0.20
     Holdings
    -0.20
     Hack
    -0.20
     Highway
    -0.17
     Heard
    -0.17
     Helm
    -0.16
     Homework
    -0.16
     Herb
    -0.16
     Hacker
    -0.16
     Handler
    -0.16
    POSITIVE LOGITS
     h
    1.44
    .h
    0.78
    $h
    0.70
    =h
    0.68
    *h
    0.65
    :h
    0.62
    (h
    0.59
    Âłh
    0.59
    [h
    0.58
    "h
    0.58
    Act Density 0.209%

    No Known Activations