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

    Neuronpedia

    INDEX
    Explanations

    words related to legal claims and issues

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    раздо
    -0.83
    варь
    -0.67
     WAYS
    -0.65
    )':
    -0.65
    findpost
    -0.63
     ways
    -0.63
    Ndr
    -0.61
    ByUrl
    -0.61
    Descripció
    -0.59
     bagaimana
    -0.58
    POSITIVE LOGITS
     '\\;'
    0.93
    rzost
    0.80
     Finale
    0.79
    seteq
    0.77
     hini
    0.77
     Cora
    0.73
     Kiki
    0.70
     Castello
    0.69
     spermato
    0.69
     Ferdinando
    0.68
    Act Density 0.044%

    No Known Activations