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

    Neuronpedia

    INDEX
    Explanations

    references to the process of improvement or transformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cond
    -0.16
     cop
    -0.16
    ãĥ«ãĥķ
    -0.15
    ullet
    -0.15
    uze
    -0.15
    osit
    -0.14
    еÑĢж
    -0.14
    ulia
    -0.14
    à¥ĭष
    -0.14
    arte
    -0.14
    POSITIVE LOGITS
    obi
    0.16
     Chim
    0.14
    ëĬ
    0.14
     Goldberg
    0.14
    Strict
    0.14
    stad
    0.14
    ìŀij
    0.14
     Pace
    0.14
    hee
    0.13
    .hw
    0.13
    Act Density 0.262%

    No Known Activations