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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating something obvious or well-known

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "of course" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iry
    -0.81
    rouse
    -0.73
    idas
    -0.68
    bish
    -0.67
    erd
    -0.66
    Fram
    -0.63
    idy
    -0.62
    ment
    -0.58
    RANT
    -0.58
    mented
    -0.58
    POSITIVE LOGITS
    س
    0.79
    NULL
    0.74
    ña
    0.74
    onga
    0.67
    olkien
    0.64
    ãĥķãĤ©
    0.63
    forth
    0.60
    hesda
    0.59
    nit
    0.59
     spoil
    0.58
    Act Density 0.028%

    No Known Activations