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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations and expressions involving complexity and boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Felix
    -0.87
    ക്
    -0.80
    bigr
    -0.79
     Ing
    -0.76
     Ballard
    -0.74
     Gates
    -0.73
     Burg
    -0.73
    Felix
    -0.73
    anger
    -0.72
     век
    -0.72
    POSITIVE LOGITS
    -\
    1.64
    +\
    1.40
    )+\
    1.32
    =\
    1.28
    )-\
    1.27
    :\
    1.21
    =-\
    1.20
    [-\
    1.17
    }+\
    1.17
    (-\
    1.14
    Act Density 0.180%

    No Known Activations