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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that indicate large quantities or significant impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ogle
    -0.16
    squeeze
    -0.15
    lesh
    -0.15
    gle
    -0.14
    ìĬ¤íĦ°
    -0.14
    .Extension
    -0.14
     occasional
    -0.14
    ustil
    -0.14
    ende
    -0.13
    бом
    -0.13
    POSITIVE LOGITS
     multiple
    0.25
     repeat
    0.24
     Repeat
    0.23
    multiple
    0.23
    repeat
    0.23
     repeated
    0.22
     repetition
    0.22
    Repeat
    0.21
     Multiple
    0.21
     repeats
    0.21
    Act Density 0.020%

    No Known Activations