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

    Neuronpedia

    INDEX
    Explanations

    terms related to masking or filters in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .mixin
    -0.18
    ndef
    -0.16
    ihat
    -0.15
     Rosenstein
    -0.15
    lernen
    -0.15
    istically
    -0.15
    ADX
    -0.15
    asmus
    -0.15
    _EXTENDED
    -0.14
    ichten
    -0.14
    POSITIVE LOGITS
    abella
    0.16
    ny
    0.15
    Æ°á»Ľ
    0.15
    rc
    0.14
    ric
    0.14
    lán
    0.14
    447
    0.14
    ilden
    0.14
    ivet
    0.14
    oppers
    0.14
    Act Density 0.003%

    No Known Activations