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

    Neuronpedia

    INDEX
    Explanations

    phrases related to exaggeration or hyperbole

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤĴè¦ĭãĤĭ
    -0.17
    âĢ¦"↵↵
    -0.17
     Sesso
    -0.16
    ffect
    -0.15
    .generated
    -0.14
    eparator
    -0.14
    ãģ£ãģį
    -0.14
    .xmlbeans
    -0.14
    âĢ¦”↵↵
    -0.14
    Ïħμ
    -0.14
    POSITIVE LOGITS
     anyone
    0.40
    ?
    0.38
     anybody
    0.33
     FT
    0.30
     Anyone
    0.28
     is
    0.28
     indeed
    0.25
     perhaps
    0.25
     yes
    0.25
    !
    0.25
    Act Density 0.810%

    No Known Activations