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

    Neuronpedia

    INDEX
    Explanations

    phrases related to discussions and negotiations

    oai_token-act-pair · gpt-3.5-turbo

    instances of conjunctions or transitional phrases, particularly those indicating contrast or sequence in discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è£ħ
    -0.67
    robe
    -0.66
    arted
    -0.65
    ãĥĩ
    -0.64
    ahan
    -0.60
    gres
    -0.60
    eware
    -0.60
    versive
    -0.59
    ?????-?????-
    -0.59
    ighed
    -0.58
    POSITIVE LOGITS
     albeit
    1.17
     because
    1.04
     although
    1.02
     but
    1.02
     insofar
    0.96
     thanks
    0.95
    because
    0.95
     namely
    0.94
     yes
    0.93
     alas
    0.92
    Act Density 0.289%

    No Known Activations