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

    Neuronpedia

    INDEX
    Explanations

    specific terminology related to coding or programming functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    891
    -0.15
    890
    -0.15
    ux
    -0.15
    pile
    -0.15
    amedi
    -0.15
    enge
    -0.14
    867
    -0.14
    assin
    -0.14
    вед
    -0.14
     supers
    -0.14
    POSITIVE LOGITS
    EMPL
    0.15
    avit
    0.15
    ropa
    0.14
    aren
    0.14
     Ðļаб
    0.14
    _GRE
    0.14
    icine
    0.14
    oty
    0.13
    質
    0.13
    ths
    0.13
    Act Density 0.002%

    No Known Activations