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

    Neuronpedia

    INDEX
    Explanations

    text related to personal experiences and interactions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to personal experiences and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udder
    -0.65
    Known
    -0.64
     Males
    -0.63
    currently
    -0.63
    ielding
    -0.63
     wearer
    -0.62
    FIG
    -0.61
    SPONSORED
    -0.61
     Their
    -0.59
     forthcoming
    -0.59
    POSITIVE LOGITS
     myself
    1.04
     yesterday
    0.92
     intending
    0.76
     kidding
    0.75
     [
    0.71
     aback
    0.68
     ['
    0.67
    poke
    0.66
    netflix
    0.66
     ourselves
    0.66
    Act Density 0.901%

    No Known Activations