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

    Neuronpedia

    INDEX
    Explanations

    people's names

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and topics related to genitalia and cultural practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gery
    -0.80
    holes
    -0.75
    escape
    -0.74
    udeb
    -0.74
    ggle
    -0.72
    lde
    -0.72
    eming
    -0.72
    kok
    -0.71
    kers
    -0.71
    #$
    -0.70
    POSITIVE LOGITS
    ine
    0.93
    iated
    0.92
    inant
    0.89
    ially
    0.87
    aneous
    0.87
    inia
    0.84
    aneously
    0.83
    iple
    0.79
    iating
    0.77
    inations
    0.77
    Act Density 0.063%

    No Known Activations