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

    Neuronpedia

    INDEX
    Explanations

    references to spatial relationships or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    USIC
    -0.15
    Pub
    -0.15
    ÑĤин
    -0.15
    bjerg
    -0.15
    Toe
    -0.15
    Ú
    -0.15
     ì²ł
    -0.14
    ÎłÎij
    -0.14
    rise
    -0.14
    zial
    -0.14
    POSITIVE LOGITS
     Rat
    0.15
    odia
    0.15
    jon
    0.15
    ahl
    0.15
     Shannon
    0.14
    0.14
     HR
    0.14
     Wyatt
    0.14
     Ellison
    0.14
     slot
    0.13
    Act Density 0.149%

    No Known Activations