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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names with accent marks or special characters

    oai_token-act-pair · gpt-3.5-turbo

    French terms and their usage in the context of descriptions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ageddon
    -0.80
     Crus
    -0.75
     Blazers
    -0.74
     Raiders
    -0.73
     Dull
    -0.72
     Plum
    -0.70
    icit
    -0.69
     Pledge
    -0.68
     Pax
    -0.66
     Sum
    -0.66
    POSITIVE LOGITS
    ÃįÃį
    1.11
    ité
    1.05
     é
    0.96
    én
    0.91
    lé
    0.91
    rique
    0.82
    ¬
    0.80
    és
    0.79
    selves
    0.78
    Ãī
    0.77
    Act Density 0.008%

    No Known Activations