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

    Neuronpedia

    INDEX
    Explanations

    words indicating belief, speculation, or conjecture about events or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    898
    -0.16
    usta
    -0.14
    yre
    -0.13
    913
    -0.13
    rech
    -0.13
    ÙĪرÙĩ
    -0.13
    agi
    -0.12
    ////////////////////////////////////////////////
    -0.12
    .todos
    -0.12
     jedná
    -0.12
    POSITIVE LOGITS
     to
    0.41
     by
    0.25
    to
    0.24
     να
    0.20
    	to
    0.19
     oleh
    0.18
    toBe
    0.16
    ãĤĴ
    0.16
     bợi
    0.16
     be
    0.16
    Act Density 0.077%

    No Known Activations