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

    Neuronpedia

    INDEX
    Explanations

    references to "templates" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leigh
    -0.17
    acre
    -0.15
    ernes
    -0.15
    UCH
    -0.15
    thro
    -0.14
    ness
    -0.14
    Beam
    -0.14
    -confidence
    -0.14
     zar
    -0.14
    orf
    -0.13
    POSITIVE LOGITS
    ton
    0.15
    ãĥ¼ãĥŃ
    0.15
    UserRole
    0.15
    TON
    0.15
    PerPixel
    0.15
    ylon
    0.15
    utton
    0.15
    /template
    0.14
    ecure
    0.14
    chooser
    0.14
    Act Density 0.010%

    No Known Activations