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

    Neuronpedia

    INDEX
    Explanations

    specific words and phrases that indicate presence and quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Folk
    -0.22
     initially
    -0.22
     initial
    -0.20
    æľĢåĪĿ
    -0.20
    initial
    -0.19
    ãģ¾ãģļ
    -0.18
     Freed
    -0.17
     preliminary
    -0.16
     Faul
    -0.16
    æķ·
    -0.15
    POSITIVE LOGITS
     ï
    0.45
     Fist
    0.40
     fir
    0.39
     fi
    0.39
    ï
    0.36
     fist
    0.35
    fir
    0.33
     Fir
    0.32
     Ist
    0.32
    -fi
    0.30
    Act Density 0.102%

    No Known Activations