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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating additional information or emphasizing a point

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "not to mention."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    twitch
    -0.75
    Constructed
    -0.69
    isf
    -0.69
    rang
    -0.68
    ells
    -0.67
    unt
    -0.67
    malink
    -0.67
    ahl
    -0.67
    car
    -0.66
    yard
    -0.66
    POSITIVE LOGITS
    lihood
    0.81
     Solitaire
    0.71
     allergies
    0.70
    epad
    0.67
     juggling
    0.66
     indexes
    0.65
     è£ıè
    0.64
     mentioning
    0.64
     dozens
    0.64
     risking
    0.64
    Act Density 0.019%

    No Known Activations