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

    Neuronpedia

    INDEX
    Explanations

    phrases related to impactful actions or events

    oai_token-act-pair · gpt-3.5-turbo

    words related to actions or movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isations
    -0.64
     concess
    -0.64
     Imran
    -0.63
    isation
    -0.62
     Aram
    -0.61
    opausal
    -0.61
     reconc
    -0.60
    icably
    -0.59
     Venezuel
    -0.59
    ised
    -0.59
    POSITIVE LOGITS
    down
    1.20
    able
    1.10
    stakes
    1.07
    ings
    1.06
    downs
    1.04
    ingly
    1.04
    stick
    1.02
    back
    1.01
    pipe
    0.99
    sticks
    0.98
    Act Density 0.261%

    No Known Activations