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

    Neuronpedia

    INDEX
    Explanations

    words related to behavioral concepts and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mun
    -0.16
    isz
    -0.16
    ahan
    -0.15
    resse
    -0.15
     kå
    -0.15
    tings
    -0.14
    lr
    -0.14
    tti
    -0.14
    ting
    -0.14
    лаÑĪ
    -0.13
    POSITIVE LOGITS
    amp
    0.17
    ateau
    0.15
    fully
    0.15
    à¸ķรà¸ĩ
    0.15
    nbsp
    0.15
    shaw
    0.15
    305
    0.14
    ilst
    0.14
    tgt
    0.14
    ascus
    0.14
    Act Density 0.015%

    No Known Activations