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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "down" and variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ylland
    -0.17
    wins
    -0.16
    cury
    -0.15
    aceous
    -0.15
    aurant
    -0.15
    zzo
    -0.15
    anmar
    -0.15
    zioni
    -0.15
    astro
    -0.14
    phalt
    -0.14
    POSITIVE LOGITS
    -down
    0.21
    ning
    0.16
    erb
    0.16
    graded
    0.16
    asser
    0.15
    ned
    0.15
    à¥įह
    0.15
    ward
    0.14
    /up
    0.14
    ed
    0.14
    Act Density 0.083%

    No Known Activations