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

    Neuronpedia

    INDEX
    Explanations

    references to emerging trends or concepts in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ners
    -0.19
    ÑĢап
    -0.16
    atura
    -0.15
    åĮĸ
    -0.15
    ned
    -0.15
    иÑĩа
    -0.15
    omial
    -0.15
    resse
    -0.15
    åĪij
    -0.14
    ordes
    -0.14
    POSITIVE LOGITS
    ence
    0.16
    prising
    0.16
    iah
    0.15
    -middle
    0.15
    peater
    0.15
    ently
    0.15
    errick
    0.15
     victorious
    0.14
    uder
    0.14
    /disable
    0.14
    Act Density 0.025%

    No Known Activations