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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and variables commonly used in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pear
    -0.16
    akat
    -0.15
    827
    -0.15
    adratic
    -0.14
    kara
    -0.14
    ucer
    -0.14
    errer
    -0.14
    _CSR
    -0.14
    uela
    -0.14
    achat
    -0.14
    POSITIVE LOGITS
     constants
    0.19
     Mall
    0.17
     smallest
    0.16
     neighborhood
    0.16
     epsilon
    0.15
    isches
    0.15
     neighborhoods
    0.15
     constant
    0.15
     neighbourhood
    0.15
     Constants
    0.15
    Act Density 0.252%

    No Known Activations