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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to taste and preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thon
    -0.17
    ham
    -0.15
    nst
    -0.14
     Optim
    -0.14
    rie
    -0.14
    istration
    -0.14
    wel
    -0.14
    ales
    -0.14
    ildo
    -0.14
    118
    -0.13
    POSITIVE LOGITS
    iller
    0.18
    formation
    0.16
    Formation
    0.15
    quila
    0.15
    itan
    0.14
     Watkins
    0.14
     YYS
    0.14
    ikt
    0.14
    _cmos
    0.14
    .Formatter
    0.14
    Act Density 0.018%

    No Known Activations