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

    Neuronpedia

    INDEX
    Explanations

    references to marginalized or specific groups of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ombo
    -0.17
    hire
    -0.17
    ç»ĩ
    -0.16
    arton
    -0.15
    Singleton
    -0.15
    omba
    -0.15
    uke
    -0.15
    squeeze
    -0.15
    dsl
    -0.14
    857
    -0.14
    POSITIVE LOGITS
    /rand
    0.16
    uteur
    0.15
    .Parcelable
    0.15
    /Typography
    0.14
     guarded
    0.14
    eland
    0.14
    .patch
    0.14
    //{{
    0.13
     scatter
    0.13
     cancell
    0.13
    Act Density 0.014%

    No Known Activations