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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to mathematical equations and proofs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kå
    -0.17
    openh
    -0.15
    pillar
    -0.15
    най
    -0.15
    zoom
    -0.15
    oplevel
    -0.14
    ulent
    -0.14
    лÑıв
    -0.14
    vox
    -0.14
    оÑĤÑĮ
    -0.14
    POSITIVE LOGITS
    ãĥĥãĥĦ
    0.16
    áž
    0.16
    dzi
    0.15
    วร
    0.15
    iyan
    0.14
    -Semit
    0.14
    jist
    0.14
    igli
    0.14
    umlu
    0.14
    899
    0.14
    Act Density 0.014%

    No Known Activations