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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to harm or injury

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irie
    -0.17
    BOR
    -0.17
    heimer
    -0.15
     dõi
    -0.15
    CKET
    -0.15
    born
    -0.15
    ander
    -0.15
    ÅĻ
    -0.14
    isman
    -0.13
    si
    -0.13
    POSITIVE LOGITS
    ummer
    0.16
    $MESS
    0.15
    adol
    0.15
     Cv
    0.15
    /weather
    0.14
    hur
    0.14
    κε
    0.14
    /loose
    0.14
    aceutical
    0.14
    ">//
    0.14
    Act Density 0.035%

    No Known Activations