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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating questioning or expressing gratitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avour
    -0.16
    altung
    -0.15
    ynes
    -0.15
    uther
    -0.15
    psc
    -0.14
    burgh
    -0.14
    ynec
    -0.13
    оÑĢож
    -0.13
    ovan
    -0.13
    кÑĥÑĢ
    -0.13
    POSITIVE LOGITS
     proxy
    0.16
     indul
    0.16
     gangbang
    0.15
    tank
    0.15
    èĥ
    0.15
     Painter
    0.15
     cogn
    0.15
    cpy
    0.14
     Interr
    0.14
    gent
    0.14
    Act Density 0.032%

    No Known Activations