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

    Neuronpedia

    INDEX
    Explanations

    words related to absolute statements or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orp
    -0.15
    uldu
    -0.15
    िषय
    -0.14
     pend
    -0.14
    uld
    -0.14
    stoff
    -0.13
     Dek
    -0.13
    زÙħاÙĨ
    -0.13
     Obj
    -0.13
    .Rendering
    -0.13
    POSITIVE LOGITS
     --
    0.17
    legen
    0.15
    clave
    0.15
    æĴĥ
    0.15
     ("
    0.15
     Washington
    0.14
    grim
    0.14
     Bush
    0.14
    htar
    0.14
     regularly
    0.14
    Act Density 0.000%

    No Known Activations