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

    Neuronpedia

    INDEX
    Explanations

    references to high-quality versions or formats of media, especially those that highlight marked improvements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    posable
    -0.16
    AMA
    -0.15
    iero
    -0.13
    anın
    -0.12
    oad
    -0.12
    .Typed
    -0.12
    lero
    -0.12
    .Txt
    -0.12
    omor
    -0.12
    VEC
    -0.12
    POSITIVE LOGITS
     version
    1.19
     versions
    1.01
    version
    0.95
     Version
    0.91
    -version
    0.91
    çīĪæľ¬
    0.90
     VERSION
    0.84
    _version
    0.84
    Version
    0.82
    .version
    0.82
    Act Density 0.296%

    No Known Activations