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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases associated with evaluations or descriptions of events and situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Äĥn
    -0.17
    ulen
    -0.15
     ect
    -0.14
    985
    -0.14
    UCT
    -0.14
    uzzi
    -0.14
     Brotherhood
    -0.14
    çī
    -0.14
    iffin
    -0.14
    ateurs
    -0.14
    POSITIVE LOGITS
    arend
    0.16
    aska
    0.15
     Zack
    0.14
     Tir
    0.14
    é½
    0.14
    leck
    0.14
    ÃŃm
    0.14
     Tunnel
    0.14
     Zak
    0.13
    ái
    0.13
    Act Density 0.003%

    No Known Activations