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

    Neuronpedia

    INDEX
    Explanations

    mathematical concepts and relationships in a formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lap
    -0.15
     conv
    -0.15
     lap
    -0.14
    cov
    -0.14
    766
    -0.14
     dumps
    -0.14
    è¾
    -0.13
     bay
    -0.13
    amiliar
    -0.13
     convention
    -0.13
    POSITIVE LOGITS
     upper
    0.19
     conject
    0.19
     bounds
    0.18
     unsett
    0.18
    _classification
    0.18
     Upper
    0.17
     affirmative
    0.17
     dispro
    0.17
    sharp
    0.17
     Counter
    0.17
    Act Density 0.085%

    No Known Activations