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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political affiliations

    oai_token-act-pair · gpt-3.5-turbo

    sentences that contain a full stop or period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     spor
    -0.78
     volunte
    -0.76
     rall
    -0.75
     frequently
    -0.73
     uncovered
    -0.73
     deliber
    -0.72
     ranged
    -0.72
    undai
    -0.71
     sensit
    -0.71
     scrim
    -0.71
    POSITIVE LOGITS
     Which
    1.29
     Anything
    1.21
     Literally
    1.20
     And
    1.19
     Its
    1.19
     Meaning
    1.18
     Everything
    1.17
     Therefore
    1.16
     Congratulations
    1.15
     Anyway
    1.14
    Act Density 0.651%

    No Known Activations