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

    Neuronpedia

    INDEX
    Explanations

    references to barriers in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     sauvages
    -0.75
     peindre
    -0.73
     guste
    -0.66
    Lob
    -0.66
     chimiques
    -0.65
     برانيه
    -0.63
     äldre
    -0.62
     profonde
    -0.61
    ztés
    -0.61
     mortes
    -0.60
    POSITIVE LOGITS
     barriers
    1.96
     barrier
    1.85
     Barriers
    1.78
     Barrier
    1.73
     obstacles
    1.62
    barrier
    1.62
     obstacle
    1.61
    Barriers
    1.60
    Barrier
    1.55
    obstacles
    1.34
    Act Density 0.033%

    No Known Activations