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

    Neuronpedia

    INDEX
    Explanations

    statements indicating negation or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roc
    -0.19
    ãĤ¥
    -0.18
    sb
    -0.17
    phies
    -0.16
    rian
    -0.16
    seed
    -0.15
    land
    -0.15
    ENCES
    -0.15
    strpos
    -0.15
    reu
    -0.15
    POSITIVE LOGITS
    /all
    0.22
    none
    0.19
     of
    0.19
    NONE
    0.18
    erg
    0.18
    anners
    0.17
    None
    0.17
    theless
    0.16
    THING
    0.16
    :mysql
    0.16
    Act Density 0.013%

    No Known Activations