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

    Neuronpedia

    INDEX
    Explanations

    mentions of authoritative roles and social issues related to marginalized groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     saites
    -0.52
    Gweler
    -0.40
    providedIn
    -0.38
    Бележки
    -0.37
    bner
    -0.37
    hyrchwyd
    -0.36
    ptonshire
    -0.36
     rispetto
    -0.36
     badly
    -0.36
    ỗng
    -0.36
    POSITIVE LOGITS
    msgTypes
    0.57
    +#+#
    0.47
    FDRE
    0.46
    sodik
    0.46
    UserScript
    0.46
    BooleanField
    0.45
    enderror
    0.45
    IndentedString
    0.44
    ViewImports
    0.44
     ſer
    0.44
    Act Density 1.563%

    No Known Activations