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

    Neuronpedia

    INDEX
    Explanations

    mentions of physical locations and activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    TPP
    -0.82
    conom
    -0.75
    amus
    -0.72
    INESS
    -0.71
    FF
    -0.69
    Reports
    -0.68
    waters
    -0.66
    ults
    -0.65
    ¯¯¯¯
    -0.64
    ########
    -0.63
    POSITIVE LOGITS
     behalf
    1.16
     occasion
    1.07
     top
    1.05
     display
    1.03
    screen
    1.02
    etime
    0.98
    coming
    0.97
    sets
    0.96
    erous
    0.95
    eday
    0.93
    Act Density 0.154%

    No Known Activations