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

    Neuronpedia

    INDEX
    Explanations

    mentions of supernatural or mysterious entities, events, or phenomena

    oai_token-act-pair · gpt-3.5-turbo

    the word "spect" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Belt
    -0.60
     tender
    -0.59
    backer
    -0.59
     disembark
    -0.57
     9000
    -0.57
     LIFE
    -0.57
    etheless
    -0.56
    heads
    -0.56
     dinner
    -0.56
    Fac
    -0.55
    POSITIVE LOGITS
    acular
    1.40
    rums
    1.30
    rosc
    1.28
    acles
    1.19
    acle
    1.17
    ators
    1.13
    rogram
    1.12
    rum
    1.12
    ator
    1.04
    rils
    1.01
    Act Density 0.030%

    No Known Activations