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

    Neuronpedia

    INDEX
    Explanations

    adverbs ending in 'ly'

    oai_token-act-pair · gpt-3.5-turbo

    transitional phrases and qualifiers in discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "},"
    -0.77
    aily
    -0.67
    /"
    -0.66
    ocaust
    -0.64
    kamp
    -0.63
    kefeller
    -0.61
    addons
    -0.60
    "))
    -0.60
    clock
    -0.59
    ilater
    -0.58
    POSITIVE LOGITS
     speaking
    1.11
    ,
    0.93
    adays
    0.80
     there
    0.72
    speaking
    0.72
    ,.
    0.71
    ,,
    0.71
    !,
    0.70
    ,...
    0.68
     it
    0.66
    Act Density 0.175%

    No Known Activations