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

    Neuronpedia

    INDEX
    Explanations

    spokespersons or representatives in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to spokespersons or official statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dream
    -0.74
    avery
    -0.73
    life
    -0.65
    bat
    -0.65
    awar
    -0.64
    ench
    -0.63
    bows
    -0.63
    burn
    -0.62
    imeo
    -0.62
     bondage
    -0.61
    POSITIVE LOGITS
     Steph
    0.77
     spokesperson
    0.76
    onse
    0.76
    atography
    0.74
    uted
    0.71
     phyl
    0.70
     clarified
    0.69
    olicy
    0.69
    ature
    0.67
    clinton
    0.67
    Act Density 0.016%

    No Known Activations