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

    Neuronpedia

    INDEX
    Explanations

    words related to written communication

    oai_token-act-pair · gpt-3.5-turbo

    references to correspondence and communication in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rug
    -0.92
    udic
    -0.91
    emonic
    -0.83
    ars
    -0.81
    iser
    -0.78
    onom
    -0.77
    ggle
    -0.76
    OWER
    -0.76
    ock
    -0.75
    umen
    -0.74
    POSITIVE LOGITS
    schild
    0.99
     correspondence
    0.97
    DragonMagazine
    0.83
    oire
    0.74
     FANTASY
    0.73
    ilial
    0.73
    ity
    0.73
    ritten
    0.73
     toile
    0.69
     Correspond
    0.68
    Act Density 0.028%

    No Known Activations