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

    Neuronpedia

    INDEX
    Explanations

    references to physical or metaphorical centers of significance or focus in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    centage
    -0.15
     Centre
    -0.15
    ument
    -0.15
    endor
    -0.15
    lore
    -0.15
    ÑĮÑİÑĤ
    -0.15
    ÙĪÙĨا
    -0.14
    omu
    -0.14
     lee
    -0.14
    ROOT
    -0.14
    POSITIVE LOGITS
     gravity
    0.26
    pieces
    0.24
    fold
    0.22
    point
    0.20
    gravity
    0.20
     Gravity
    0.20
     attention
    0.20
    Gravity
    0.19
     focus
    0.19
    most
    0.18
    Act Density 0.050%

    No Known Activations