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

    Neuronpedia

    INDEX
    Explanations

    references to numerical strength or forces in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ế
    -0.17
    klady
    -0.16
    elves
    -0.16
     deposit
    -0.16
    avr
    -0.15
     ìŀ¡
    -0.15
    orbit
    -0.15
    deposit
    -0.15
    íĥĦ
    -0.15
    åħĥ
    -0.15
    POSITIVE LOGITS
     strength
    0.15
     edge
    0.14
    OfSize
    0.14
     box
    0.14
     against
    0.14
     æ¬
    0.14
    strength
    0.14
    /lg
    0.14
     Conserv
    0.14
    ת
    0.14
    Act Density 0.346%

    No Known Activations