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

    Neuronpedia

    INDEX
    Explanations

    words related to selections or draft picks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cats
    -0.17
     analog
    -0.16
     conte
    -0.15
    isc
    -0.14
     pump
    -0.14
    .Toolkit
    -0.14
    _PRIV
    -0.14
    eward
    -0.14
    Forbidden
    -0.14
    athy
    -0.13
    POSITIVE LOGITS
    ProgressHUD
    0.17
    fur
    0.15
    enton
    0.15
    marshaller
    0.14
    ombo
    0.14
    ibri
    0.14
    ìĨIJ
    0.14
    боÑĤ
    0.13
    topl
    0.13
    oyer
    0.13
    Act Density 0.013%

    No Known Activations