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

    Neuronpedia

    INDEX
    Explanations

    pronouns followed by a verb indicating interaction between multiple entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "each other."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Variety
    -0.72
     Lans
    -0.66
     Winter
    -0.62
    Ń·
    -0.60
     Sweeney
    -0.60
     Presbyter
    -0.60
     1962
    -0.59
     Grade
    -0.59
     1897
    -0.58
     Gothic
    -0.58
    POSITIVE LOGITS
    worldly
    1.34
    inant
    0.86
    wise
    0.81
    selves
    0.77
    breaker
    0.69
     kindred
    0.68
    stretched
    0.67
     equally
    0.62
    Redd
    0.62
     throats
    0.61
    Act Density 0.035%

    No Known Activations