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

    Neuronpedia

    INDEX
    Explanations

    references to reactions or actions following some kind of stimulus or event

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "in response to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utters
    -0.77
    \\\\\\\\
    -0.72
    avis
    -0.71
    rament
    -0.71
    ccording
    -0.71
    flo
    -0.71
     Dull
    -0.71
    gin
    -0.69
    stall
    -0.69
    oiler
    -0.68
    POSITIVE LOGITS
     thereto
    0.86
     briefs
    0.76
     posture
    0.75
     response
    0.73
    ively
    0.73
     responses
    0.72
     guiActiveUn
    0.65
    ivated
    0.64
     feedback
    0.63
    reply
    0.63
    Act Density 0.014%

    No Known Activations