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

    Neuronpedia

    INDEX
    Explanations

    references to scientific methodologies or experimental protocols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    *)((
    -0.15
    ики
    -0.14
    oir
    -0.14
    oss
    -0.14
    redient
    -0.14
    noch
    -0.14
    üç
    -0.14
    ossa
    -0.14
    ieg
    -0.14
    ¢
    -0.13
    POSITIVE LOGITS
    ework
    0.16
    лиÑĪ
    0.15
    atin
    0.14
    iska
    0.14
    ÑĥÑĤи
    0.14
     Clover
    0.14
     nær
    0.13
    顾
    0.13
    urate
    0.13
    ï¼³
    0.13
    Act Density 0.001%

    No Known Activations