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

    Neuronpedia

    INDEX
    Explanations

    verbs or phrases related to actions or events in a historical or informative context

    oai_token-act-pair · gpt-3.5-turbo

    verbs and phrases related to accusations and assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soType
    -0.84
    stack
    -0.79
    */(
    -0.74
    Sensor
    -0.73
    AppData
    -0.72
    bite
    -0.71
    Bed
    -0.69
    Mom
    -0.67
    thank
    -0.67
    Drop
    -0.66
    POSITIVE LOGITS
     formatting
    0.72
    itled
    0.69
     nudity
    0.68
     mention
    0.67
    hov
    0.66
     humor
    0.66
     foreigners
    0.66
     references
    0.64
     specifically
    0.64
     homosexuality
    0.63
    Act Density 0.520%

    No Known Activations