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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "say" and its various forms, highlighting expressions of speech and communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aney
    -0.16
    stead
    -0.16
    roy
    -0.15
    _IL
    -0.15
    659
    -0.15
    antro
    -0.15
     اÙĦظ
    -0.15
    ¯
    -0.14
    iling
    -0.14
     Ext
    -0.14
    POSITIVE LOGITS
    anka
    0.17
    çĴĥ
    0.16
    ordes
    0.16
    ковод
    0.15
     Liberties
    0.15
    ãĥ¼ãĥī
    0.15
    othermal
    0.15
     Tits
    0.15
    assen
    0.14
    ophon
    0.14
    Act Density 0.084%

    No Known Activations