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

    Neuronpedia

    INDEX
    Explanations

    phrases requesting or suggesting someone's presence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "come" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ²¾
    -0.83
    ricular
    -0.77
    orthodox
    -0.77
     tiss
    -0.74
    ruff
    -0.74
    bons
    -0.74
    nesota
    -0.73
    ignty
    -0.73
    versible
    -0.73
    ikhail
    -0.73
    POSITIVE LOGITS
     undone
    0.98
     forth
    0.94
     hither
    0.86
     INTO
    0.86
     into
    0.85
     ashore
    0.83
     WRITE
    0.81
     up
    0.80
     out
    0.80
     forward
    0.76
    Act Density 0.081%

    No Known Activations