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

    Neuronpedia

    INDEX
    Explanations

    references to physical locations or sides of objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    side of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Beijos
    -0.35
     autorytatywna
    -0.34
    assertIs
    -0.33
     varier
    -0.32
     yến
    -0.32
     proportionately
    -0.31
     ahor
    -0.31
     procé
    -0.31
    วม
    -0.30
     mln
    -0.30
    POSITIVE LOGITS
     side
    1.26
    side
    1.23
     Side
    1.21
    Side
    1.19
     Sides
    1.17
     SIDE
    1.16
     sides
    1.15
    sides
    1.09
    SIDE
    1.04
    Sides
    1.02
    Act Density 0.008%

    No Known Activations