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

    Neuronpedia

    INDEX
    Explanations

    references to community leaders and their warnings or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    colgante
    -0.48
     zubehör
    -0.47
     vectorielle
    -0.47
    homonymie
    -0.45
    iotensin
    -0.44
     cír
    -0.44
     disegni
    -0.44
    Ligações
    -0.43
     memen
    -0.42
    يميديا
    -0.42
    POSITIVE LOGITS
     Rabbi
    0.68
     Goldstein
    0.68
     rabbi
    0.65
     Shapiro
    0.62
     Frankel
    0.62
     Feldman
    0.60
     Silverman
    0.58
    Rabbi
    0.57
     Cohen
    0.57
     Epstein
    0.56
    Act Density 0.512%

    No Known Activations