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

    Neuronpedia

    INDEX
    Explanations

    instances where examples or cases are cited

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    OOOOOOOO
    -0.82
    oredCriteria
    -0.78
     Sadler
    -0.72
     Umberto
    -0.71
     Metab
    -0.69
    ه
    -0.69
     HOM
    -0.68
    äler
    -0.68
    eaway
    -0.66
    XXXXXXXX
    -0.66
    POSITIVE LOGITS
     Airs
    0.66
     sobretudo
    0.63
     antaranya
    0.62
    antaranya
    0.61
    ——–
    0.61
    dill
    0.60
     Nhưng
    0.60
    till
    0.58
     própria
    0.58
    ضر
    0.58
    Act Density 0.003%

    No Known Activations