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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions that involve physical movement or change

    oai_token-act-pair · gpt-3.5-turbo

    action verbs that indicate significant activities or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ][
    -0.70
    ortium
    -0.63
    esa
    -0.62
    enny
    -0.60
    ibrary
    -0.60
    edged
    -0.59
    mite
    -0.59
    reshold
    -0.58
    OA
    -0.57
    arel
    -0.56
    POSITIVE LOGITS
     accordingly
    1.23
     thereafter
    0.93
     consequently
    0.89
     alike
    0.89
     afterward
    0.79
     himself
    0.79
     afterwards
    0.75
     therein
    0.75
     consequ
    0.72
     thereby
    0.71
    Act Density 0.387%

    No Known Activations