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

    Neuronpedia

    INDEX
    Explanations

    terms related to investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /browse
    -0.19
    473
    -0.16
    endale
    -0.16
    ska
    -0.16
    raith
    -0.16
    ahn
    -0.15
    orna
    -0.14
    ofire
    -0.14
    DataExchange
    -0.14
    ëł
    -0.14
    POSITIVE LOGITS
    yd
    0.19
    bis
    0.15
    SEX
    0.14
     PIPE
    0.14
    neau
    0.14
     appearances
    0.14
    íĥ
    0.13
    ÙĪ
    0.13
    allest
    0.13
     LGPL
    0.13
    Act Density 0.001%

    No Known Activations