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

    Neuronpedia

    INDEX
    Explanations

    phrases related to regulation and legal discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     steroids
    -0.74
    abouts
    -0.71
     reserves
    -0.66
     Ferdinand
    -0.64
     whereabouts
    -0.63
     displeasure
    -0.63
    rity
    -0.63
     admin
    -0.62
     acre
    -0.61
    lled
    -0.61
    POSITIVE LOGITS
    ³³³³³³³³
    1.14
    ³³³³³³³³³³³³³³³³
    1.12
    ³³³
    1.07
    ³³³³
    1.04
    "...
    0.93
    "âĢ¦
    0.87
    Feature
    0.81
    ³³
    0.79
    Liter
    0.78
    Fre
    0.77
    Act Density 0.062%

    No Known Activations