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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating negation or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èį
    -0.15
    ROC
    -0.15
    anches
    -0.15
    pedo
    -0.15
    avo
    -0.15
    ÚĨÙĩ
    -0.15
    roc
    -0.14
    pie
    -0.14
    _CN
    -0.14
    ropolis
    -0.14
    POSITIVE LOGITS
    THING
    0.19
     of
    0.19
    erg
    0.16
    olen
    0.15
    ERGY
    0.15
    esse
    0.14
    /all
    0.14
    ereal
    0.14
    better
    0.14
     Schneider
    0.14
    Act Density 0.012%

    No Known Activations