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

    Neuronpedia

    INDEX
    Explanations

    elements related to experimental setup and results in research papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anten
    -0.07
    ein
    -0.06
    elp
    -0.06
    asn
    -0.06
    zeit
    -0.06
    å¾Ħ
    -0.06
    inu
    -0.06
    errer
    -0.06
     straight
    -0.06
    enever
    -0.06
    POSITIVE LOGITS
    owitz
    0.08
    ju
    0.06
    igua
    0.06
    urai
    0.06
    -webpack
    0.06
    سبة
    0.06
    ÑĮÑİÑĤ
    0.06
    uild
    0.06
     Torch
    0.06
    caption
    0.06
    Act Density 0.070%

    No Known Activations