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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences related to turning something on

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "turn on"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    far
    -0.81
    WA
    -0.77
    BUT
    -0.74
    perse
    -0.73
    Cat
    -0.71
    SourceFile
    -0.71
    mere
    -0.71
    rough
    -0.71
    WR
    -0.70
    hammer
    -0.68
    POSITIVE LOGITS
    shore
    0.92
    etime
    0.91
    erous
    0.87
    yx
    0.82
     steroids
    0.80
     autop
    0.80
     behalf
    0.80
     axis
    0.79
     occasion
    0.78
    itored
    0.75
    Act Density 0.049%

    No Known Activations