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

    Neuronpedia

    INDEX
    Explanations

    document structure elements and programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rollo
    -0.44
    styleable
    -0.44
     orch
    -0.43
     rollers
    -0.42
    tagHelper
    -0.42
     surla
    -0.42
     Rolling
    -0.42
    ultier
    -0.41
    rew
    -0.41
     rolled
    -0.40
    POSITIVE LOGITS
     kasarigan
    0.60
    ws
    0.56
    ⓧ
    0.53
    __":
    0.49
     Lim
    0.48
    __':
    0.48
     mergeFrom
    0.47
     Tha
    0.47
    Tha
    0.46
     Mexique
    0.46
    Act Density 1.275%

    No Known Activations