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

    Neuronpedia

    INDEX
    Explanations

    references to societal issues and personal experiences related to prejudice and injustice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    velle
    -0.15
     ë¬
    -0.15
    Disposition
    -0.15
    .Logf
    -0.15
    KNOWN
    -0.15
    oto
    -0.14
    iamo
    -0.14
    ulumi
    -0.14
    .scalablytyped
    -0.14
    .Startup
    -0.14
    POSITIVE LOGITS
    ollah
    0.19
     involved
    0.17
     involve
    0.15
     McG
    0.15
     involvement
    0.14
     selections
    0.14
     formerly
    0.14
    ocratic
    0.14
    essay
    0.14
    aub
    0.13
    Act Density 0.341%

    No Known Activations