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

    Neuronpedia

    INDEX
    Explanations

    references to academic citations or author collaborations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esh
    -0.19
    erland
    -0.17
    culos
    -0.16
    andex
    -0.15
    _CALLBACK
    -0.15
    бом
    -0.15
    byn
    -0.15
    enny
    -0.15
    ymm
    -0.15
    adu
    -0.14
    POSITIVE LOGITS
    0.15
    hap
    0.14
    rc
    0.14
     BMC
    0.14
    enders
    0.14
    td
    0.14
    ilm
    0.14
    VRT
    0.14
    ÑĶм
    0.13
    /Core
    0.13
    Act Density 0.016%

    No Known Activations