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

    Neuronpedia

    INDEX
    Explanations

    characteristics related to feedback and ratings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     surla
    -0.70
    Datuak
    -0.61
    rungsseite
    -0.60
     avoidable
    -0.59
    ScopeManager
    -0.57
    scalatest
    -0.57
    :+:
    -0.56
    rrggbb
    -0.55
     structurally
    -0.55
     forgotten
    -0.54
    POSITIVE LOGITS
    عالی
    0.50
    Хорошо
    0.48
    Muito
    0.46
     molt
    0.46
    identiality
    0.46
     kasarigan
    0.45
     committees
    0.45
     patrols
    0.45
    خیلی
    0.44
     Freedman
    0.44
    Act Density 0.022%

    No Known Activations