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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal charges and accusations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    archiviato
    -0.55
    TagMode
    -0.54
    󠁮
    -0.52
    الدراسه
    -0.48
     integridad
    -0.47
     fatica
    -0.47
     referrerpolicy
    -0.46
    NameInMap
    -0.45
     GenerationType
    -0.44
    ptid
    -0.43
    POSITIVE LOGITS
     CHAR
    1.08
     char
    0.96
     charging
    0.95
    CHAR
    0.94
    Char
    0.92
    charging
    0.91
     Char
    0.89
     Charging
    0.85
     charge
    0.82
     charged
    0.81
    Act Density 0.185%

    No Known Activations