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

    Neuronpedia

    INDEX
    Explanations

    references to defense-related topics and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icode
    -0.20
     Balt
    -0.18
    plusplus
    -0.16
     ger
    -0.16
     Hlav
    -0.15
    raki
    -0.14
    имÑĥ
    -0.14
    emoc
    -0.14
    лÑıн
    -0.14
    ÑĪев
    -0.14
    POSITIVE LOGITS
     Tob
    0.17
    itel
    0.16
    æ´
    0.15
     Woods
    0.15
    iste
    0.15
    yte
    0.15
    kf
    0.15
    term
    0.14
     Mystic
    0.14
    arat
    0.14
    Act Density 0.029%

    No Known Activations