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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparison and equality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asma
    -0.15
    rial
    -0.14
    รม
    -0.14
    allas
    -0.14
    iggs
    -0.13
    rowsable
    -0.13
    çķªåı·
    -0.13
    casting
    -0.13
    ividual
    -0.13
    reon
    -0.13
    POSITIVE LOGITS
     equally
    0.26
     Tig
    0.16
    acente
    0.14
    аниÑİ
    0.14
     Rab
    0.14
    undy
    0.14
     Tiger
    0.13
    Operation
    0.13
    los
    0.13
    ANI
    0.13
    Act Density 0.066%

    No Known Activations