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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences related to actions being done

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to," indicating a focus on infinitive verbs or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     deductions
    -0.68
     deviations
    -0.61
     detached
    -0.60
     ranges
    -0.60
     transformations
    -0.60
     knots
    -0.60
     binaries
    -0.59
     crossings
    -0.59
     activated
    -0.58
     surgeon
    -0.58
    POSITIVE LOGITS
     coincide
    1.43
     commemorate
    1.42
     celebrate
    1.31
    pless
    1.22
     promote
    1.06
     accompany
    1.05
     emphasize
    1.03
     remind
    0.97
    wered
    0.96
     illustrate
    0.96
    Act Density 0.240%

    No Known Activations