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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating being the first to know or be informed about something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize being the first or the best in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igree
    -0.67
    ibaba
    -0.67
     incomp
    -0.64
     fracturing
    -0.63
     warrants
    -0.62
     unden
    -0.61
     similarities
    -0.61
    dated
    -0.59
    arching
    -0.58
     similarity
    -0.58
    POSITIVE LOGITS
    ILLE
    0.74
     lookout
    0.70
    icer
    0.68
     Sole
    0.65
    ATER
    0.64
    IDER
    0.64
     rover
    0.64
     careg
    0.62
     guiActive
    0.62
     Laser
    0.61
    Act Density 0.146%

    No Known Activations