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

    Neuronpedia

    INDEX
    Explanations

    phrases related to user input and form behavior in a digital or application context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModelIndex
    -0.15
     dostan
    -0.14
    agma
    -0.14
    benh
    -0.14
    unbind
    -0.14
    aket
    -0.13
    /pdf
    -0.13
    avel
    -0.13
    ilter
    -0.13
     Target
    -0.13
    POSITIVE LOGITS
     input
    0.36
     inputs
    0.31
    -input
    0.31
     ìŀħëł¥
    0.30
    è¾ĵåħ¥
    0.30
    input
    0.29
     Input
    0.28
    Input
    0.28
     entered
    0.27
    å¡«
    0.27
    Act Density 0.200%

    No Known Activations