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

    Neuronpedia

    INDEX
    Explanations

    sections of code or programming-related syntax

    oai_token-act-pair · gpt-3.5-turbo

    bracketed or indexed elements in structured data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ń·
    -0.96
    keye
    -0.75
    acies
    -0.71
    »Ĵ
    -0.70
    aido
    -0.68
    anooga
    -0.67
    İĭ
    -0.67
    omore
    -0.67
    hement
    -0.66
    orthy
    -0.66
    POSITIVE LOGITS
    LOG
    0.80
    (){
    0.76
    ||
    0.76
    byte
    0.76
    =(
    0.75
    ))
    0.75
    UAL
    0.74
    ################
    0.74
     =>
    0.72
    +)
    0.71
    Act Density 0.025%

    No Known Activations