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

    Neuronpedia

    INDEX
    Explanations

    the repetition and emphasis of the word "so."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    prd
    -0.18
    uisse
    -0.16
    õi
    -0.16
    kaar
    -0.15
    rott
    -0.15
    aint
    -0.15
    pr
    -0.15
    craft
    -0.15
    umm
    -0.15
    alace
    -0.15
    POSITIVE LOGITS
    -called
    0.26
    onest
    0.20
    ìį¨
    0.20
    oner
    0.19
     far
    0.19
    aping
    0.18
    ars
    0.18
    oth
    0.18
    iled
    0.16
    ester
    0.16
    Act Density 0.069%

    No Known Activations