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

    Neuronpedia

    INDEX
    Explanations

    references to directions and positions in relation to other entities or physical concepts like place, side, arm, hand, thing, gender, and direction

    oai_token-act-pair · gpt-3.5-turbo

    references to locations and spatial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tro
    -0.78
     Tray
    -0.68
    CLASSIFIED
    -0.66
    IVERS
    -0.65
    DOS
    -0.63
     Leban
    -0.61
    wolves
    -0.61
     Cla
    -0.61
    DEF
    -0.60
    BG
    -0.58
    POSITIVE LOGITS
     apiece
    0.88
     individually
    0.72
    undred
    0.71
    olson
    0.67
    ilion
    0.66
     each
    0.63
    abyte
    0.63
     stroke
    0.62
    roups
    0.62
    fecture
    0.61
    Act Density 0.143%

    No Known Activations