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

    Neuronpedia

    INDEX
    Explanations

    phrases suggesting a power dynamic or struggle for agency

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    homonymie
    -0.63
     surla
    -0.59
     Houſe
    -0.56
     Reſ
    -0.55
     Arka
    -0.54
     Majefty
    -0.53
    PreferredItem
    -0.53
     Meksiku
    -0.52
     Diſ
    -0.52
    abestanden
    -0.52
    POSITIVE LOGITS
    OGND
    0.69
    invalidate
    0.54
    henswürdigkeiten
    0.53
     }))
    0.53
    "?>
    0.50
    ModelAdmin
    0.50
    govine
    0.49
    WithIdentifier
    0.49
    ⓧ
    0.48
     manis
    0.47
    Act Density 0.007%

    No Known Activations