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

    Neuronpedia

    INDEX
    Explanations

    references to hobbies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulpt
    -0.17
    çĭIJ
    -0.15
    xin
    -0.15
    abar
    -0.15
     dese
    -0.15
    ħĮ
    -0.14
    eners
    -0.14
    atables
    -0.14
    ucker
    -0.14
    éĺµ
    -0.14
    POSITIVE LOGITS
    elin
    0.17
    sem
    0.16
     Peng
    0.16
    SEM
    0.15
     highway
    0.15
    anova
    0.15
    beer
    0.14
    egin
    0.14
    ritz
    0.14
    se
    0.14
    Act Density 0.003%

    No Known Activations