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

    Neuronpedia

    INDEX
    Explanations

    text surrounding the word "leaves" indicating departure or absence

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating the consequences or effects of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wcsstore
    -0.74
     Cosponsors
    -0.73
    intend
    -0.69
    PI
    -0.69
    idium
    -0.68
    è¦ļéĨĴ
    -0.67
    hower
    -0.64
    nir
    -0.63
    Refer
    -0.63
    andan
    -0.62
    POSITIVE LOGITS
     behind
    1.21
     unanswered
    1.04
     untouched
    1.01
     intact
    1.01
     room
    0.97
     gaping
    0.97
     Behind
    0.94
     unfinished
    0.93
     undone
    0.93
     footprints
    0.90
    Act Density 0.055%

    No Known Activations