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

    Neuronpedia

    INDEX
    Explanations

    words expressing additional information or detailing something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "also."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stice
    -0.69
    orate
    -0.69
    only
    -0.68
    regate
    -0.67
    acity
    -0.66
    orum
    -0.66
    urches
    -0.65
    gemony
    -0.65
    each
    -0.65
    ision
    -0.65
    POSITIVE LOGITS
     noteworthy
    0.94
     implicated
    0.90
     notable
    0.85
     prone
    0.84
     applicable
    0.81
     susceptible
    0.80
     known
    0.79
     responsible
    0.79
     relevant
    0.75
     possible
    0.74
    Act Density 0.114%

    No Known Activations