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

    Neuronpedia

    INDEX
    Explanations

    mentions of physical locations, specifically junctions

    oai_token-act-pair · gpt-3.5-turbo

    references to junctions and connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cember
    -0.71
    rek
    -0.69
    yre
    -0.68
    liquid
    -0.68
    ngth
    -0.64
    Winner
    -0.63
     Panic
    -0.62
    inav
    -0.62
    isable
    -0.61
     commanded
    -0.61
    POSITIVE LOGITS
    cture
    1.28
     jun
    1.18
    ctions
    0.95
     junction
    0.95
    uez
    0.82
    ences
    0.80
    hess
    0.76
    iper
    0.75
    otaur
    0.75
    unction
    0.75
    Act Density 0.024%

    No Known Activations