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

    Neuronpedia

    INDEX
    Explanations

    phrases related to consistency and coherence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -0.21
    aso
    -0.20
    eger
    -0.18
    uch
    -0.17
    gran
    -0.16
    scribe
    -0.16
    thing
    -0.16
    juan
    -0.15
    rus
    -0.14
    essler
    -0.14
    POSITIVE LOGITS
    ently
    0.32
    antly
    0.20
    cy
    0.20
    encies
    0.19
    ively
    0.18
     across
    0.18
    ency
    0.18
     Across
    0.17
    Across
    0.17
    ÛĮدا
    0.16
    Act Density 0.034%

    No Known Activations