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

    Neuronpedia

    INDEX
    Explanations

    phrases related to economic systems and political organizations

    oai_token-act-pair · gpt-3.5-turbo

    punctuations, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enf
    -0.68
    ukong
    -0.67
    ragon
    -0.66
    bucks
    -0.65
    amaz
    -0.65
    ampa
    -0.65
    =#
    -0.64
    untarily
    -0.64
    66666666
    -0.64
    azines
    -0.63
    POSITIVE LOGITS
     consisting
    1.36
     wherein
    1.26
     staffed
    1.19
     whereby
    1.17
     comprising
    1.16
     devoid
    1.15
     overseen
    1.14
     composed
    1.12
     comprised
    1.11
     combining
    1.10
    Act Density 0.333%

    No Known Activations