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

    Neuronpedia

    INDEX
    Explanations

    references to legal charges and offenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     impunity
    -0.17
    nze
    -0.15
    Å¡ov
    -0.14
    nore
    -0.13
    ouce
    -0.13
    ÙĨاÙħÙĩ
    -0.13
    kas
    -0.13
     apologies
    -0.13
    attern
    -0.12
    Å¡et
    -0.12
    POSITIVE LOGITS
     charges
    0.91
     charge
    0.79
     Charges
    0.72
    charges
    0.68
     Charge
    0.66
    charge
    0.63
     charged
    0.63
    Charge
    0.59
     charg
    0.52
     charging
    0.51
    Act Density 0.088%

    No Known Activations