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

    Neuronpedia

    INDEX
    Explanations

    words related to disappearance or events that involve disappearing

    oai_token-act-pair · gpt-3.5-turbo

    terms related to vanishing or disappearing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tennis
    -0.72
    ses
    -0.67
     plurality
    -0.65
    ios
    -0.59
     QC
    -0.58
    ocations
    -0.58
    itcher
    -0.57
     harness
    -0.56
    wyn
    -0.56
    erity
    -0.55
    POSITIVE LOGITS
     mysteriously
    1.10
     altogether
    0.94
    owship
    0.90
     unnoticed
    0.86
     abruptly
    0.86
     peacefully
    0.86
     vanish
    0.85
     disappear
    0.82
     overnight
    0.78
     entirely
    0.78
    Act Density 0.031%

    No Known Activations