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

    Neuronpedia

    INDEX
    Explanations

    terms related to permissions and allowances in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rrggbb
    -0.61
     références
    -0.60
    writeByte
    -0.55
     gars
    -0.54
     pleaſure
    -0.54
     Reverso
    -0.54
     parís
    -0.53
     bü
    -0.53
     ujednoznacz
    -0.53
    opsida
    -0.53
    POSITIVE LOGITS
     allowed
    0.79
     gelassen
    0.70
     allow
    0.67
    Letting
    0.65
    allowed
    0.65
     Allowing
    0.63
     permitem
    0.63
     allowing
    0.63
     للمعارف
    0.61
     Letting
    0.61
    Act Density 0.245%

    No Known Activations