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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to definitions and glossaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ä¸ĺ
    -0.15
    .ali
    -0.15
    øre
    -0.15
    ialis
    -0.15
    ma
    -0.14
    stateParams
    -0.14
    Closure
    -0.14
    ÑĢоиз
    -0.14
    opts
    -0.14
    224
    -0.14
    POSITIVE LOGITS
    ulo
    0.16
     Adrian
    0.15
    -events
    0.15
     klu
    0.14
     terms
    0.14
     Events
    0.14
    verity
    0.14
    events
    0.14
     events
    0.14
    undos
    0.14
    Act Density 0.065%

    No Known Activations