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

    Neuronpedia

    INDEX
    Explanations

    references to parole and related procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    parole review

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hig
    -0.46
    Gre
    -0.43
     Hig
    -0.39
     Dh
    -0.37
    См
    -0.37
     Opti
    -0.37
    think
    -0.36
    SNA
    -0.36
     Gre
    -0.36
     Highlander
    -0.36
    POSITIVE LOGITS
     parole
    2.34
     Parole
    2.22
    parole
    1.96
     paroles
    1.42
     Paroles
    1.31
     parola
    1.08
     paro
    0.97
    paroles
    0.90
     Paro
    0.77
     Probation
    0.75
    Act Density 0.006%

    No Known Activations