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

    Neuronpedia

    INDEX
    Explanations

    phrases related to working on tasks or projects

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "working on"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Bey
    -0.86
    Override
    -0.74
    Chel
    -0.71
    Jones
    -0.69
    ILA
    -0.69
    ennes
    -0.69
    flies
    -0.68
    Cry
    -0.68
    externalActionCode
    -0.67
    YY
    -0.66
    POSITIVE LOGITS
     behalf
    1.52
    eday
    0.94
     improving
    0.93
     developing
    0.82
     reforming
    0.77
     occasion
    0.76
     cultivating
    0.76
     refining
    0.75
     drafting
    0.75
     preserving
    0.74
    Act Density 0.088%

    No Known Activations