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

    Neuronpedia

    INDEX
    Explanations

    phrases related to progress or status

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to status and ongoing processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    laus
    -0.69
    anmar
    -0.68
    zzy
    -0.66
    encer
    -0.64
    STEM
    -0.63
    geons
    -0.63
    geon
    -0.62
    auts
    -0.62
    ï¸ı
    -0.61
    remlin
    -0.61
    POSITIVE LOGITS
     occasions
    1.02
     basis
    0.86
     Beh
    0.79
     occasion
    0.76
     pedest
    0.73
     projector
    0.70
    demand
    0.68
     behalf
    0.67
     Waves
    0.66
     provocation
    0.64
    Act Density 0.074%

    No Known Activations