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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating certainty or strong affirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    es
    -0.88
    er
    -0.88
    ing
    -0.83
     rootReducer
    -0.78
    cu
    -0.72
     Suárez
    -0.71
    se
    -0.71
    en
    -0.70
    xla
    -0.70
    a
    -0.68
    POSITIVE LOGITS
     houſe
    1.18
     purpoſe
    1.15
    ^(@)
    1.14
     &___
    1.02
     вікі
    1.02
     myſelf
    1.01
     ſche
    0.98
     ejus
    0.96
     ſta
    0.96
    BibitemShut
    0.95
    Act Density 0.090%

    No Known Activations