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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "ful" and its variations, indicating a focus on concepts of fulfillment and satisfaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apers
    -0.16
    eden
    -0.15
    yards
    -0.15
    ober
    -0.15
    lou
    -0.15
    egas
    -0.15
    emente
    -0.14
    اÙģت
    -0.14
    edo
    -0.14
    ello
    -0.14
    POSITIVE LOGITS
    bright
    0.31
    fil
    0.26
    fill
    0.25
    fills
    0.21
    filled
    0.21
    minate
    0.21
    ldata
    0.20
    fillable
    0.19
    led
    0.19
    cr
    0.19
    Act Density 0.005%

    No Known Activations