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

    Neuronpedia

    INDEX
    Explanations

    references to encountering or discovering new information or objects

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "came across."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rouse
    -0.72
    cknowled
    -0.69
    cise
    -0.66
    za
    -0.65
    ially
    -0.59
     ejac
    -0.58
     sealing
    -0.57
    ners
    -0.56
     sod
    -0.56
     dedication
    -0.56
    POSITIVE LOGITS
    ãĤ´ãĥ³
    0.81
    omething
    0.76
    Ĥ¬
    0.72
    etter
    0.72
    rocal
    0.70
    ifferent
    0.69
    akeru
    0.68
    PF
    0.66
    ãĤ¼
    0.66
    ãĥīãĥ©ãĤ´ãĥ³
    0.66
    Act Density 0.017%

    No Known Activations