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

    Neuronpedia

    INDEX
    Explanations

    dialogue between characters

    oai_token-act-pair · gpt-3.5-turbo

    actions and interactions between characters in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    forestation
    -0.68
    oÄŁ
    -0.63
    osate
    -0.63
    glers
    -0.62
    hovah
    -0.62
    ividual
    -0.61
    iterranean
    -0.58
    indal
    -0.58
    milo
    -0.58
    senal
    -0.57
    POSITIVE LOGITS
     softly
    0.78
     startled
    0.77
     nervously
    0.77
     gently
    0.77
     angrily
    0.75
     grin
    0.74
     soothing
    0.72
     gloom
    0.72
     yawn
    0.70
     grinning
    0.70
    Act Density 0.718%

    No Known Activations