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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "do"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pedia
    -0.16
    isz
    -0.15
    prof
    -0.15
    åłĨ
    -0.14
    deaux
    -0.14
    706
    -0.14
    opoulos
    -0.13
    iston
    -0.13
    ì¦Ŀ
    -0.13
    .meta
    -0.13
    POSITIVE LOGITS
     so
    0.27
    igin
    0.19
     So
    0.15
    rosso
    0.15
    so
    0.14
    itant
    0.14
    idden
    0.13
    AIN
    0.13
    .so
    0.13
     onResponse
    0.13
    Act Density 0.038%

    No Known Activations