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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "as" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģĩ
    -0.18
    bler
    -0.16
    OKIE
    -0.15
     evidenced
    -0.15
    astered
    -0.15
    оваÑĢи
    -0.15
    èŀ
    -0.14
    raud
    -0.14
    ogl
    -0.14
    eba
    -0.14
    POSITIVE LOGITS
    atur
    0.16
    ÙıÙĩ
    0.15
    aina
    0.15
     opposed
    0.15
     far
    0.14
     sı
    0.14
     backs
    0.14
    /Instruction
    0.14
    GORITH
    0.14
    eec
    0.14
    Act Density 0.049%

    No Known Activations