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

    Neuronpedia

    INDEX
    Explanations

    references to harm or negative events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lea
    -0.15
    agna
    -0.14
    ivas
    -0.14
    olley
    -0.14
    iki
    -0.14
    ael
    -0.14
    ken
    -0.14
    atra
    -0.13
    hangi
    -0.13
    coni
    -0.13
    POSITIVE LOGITS
    çļĦæĺ¯
    0.15
     because
    0.15
    porte
    0.15
    /favicon
    0.14
    ãģłãģijãģ§
    0.14
    .Unsupported
    0.14
     also
    0.14
    ashi
    0.14
    اسÙħ
    0.14
    ark
    0.14
    Act Density 0.318%

    No Known Activations