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

    Neuronpedia

    INDEX
    Explanations

    historical references and significant societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apel
    -0.15
     myself
    -0.15
    panels
    -0.15
     lately
    -0.14
    _syntax
    -0.14
    ãĤĦãģĻ
    -0.14
     Maj
    -0.14
    ål
    -0.14
    /Gate
    -0.14
    ngo
    -0.13
    POSITIVE LOGITS
     ëĭ¹ìĭľ
    0.40
     tehdy
    0.28
     ÑĤогда
    0.28
     early
    0.27
     era
    0.25
     contempor
    0.25
     contemporary
    0.25
    early
    0.24
     Era
    0.23
    å½ĵ
    0.23
    Act Density 0.238%

    No Known Activations