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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate repetition or reiteration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     egiten
    -0.61
     wish
    -0.49
    skap
    -0.47
     بيها
    -0.47
    ണ
    -0.46
     right
    -0.46
    setRight
    -0.45
    Assertions
    -0.44
    (-
    -0.44
    RIGHT
    -0.43
    POSITIVE LOGITS
     betweenstory
    0.83
    Again
    0.78
    ThemeOverlay
    0.78
    исленность
    0.77
    同じく
    0.74
     Again
    0.73
    tagHelperRunner
    0.70
    uesia
    0.69
     ProtoMessage
    0.69
     ibid
    0.68
    Act Density 0.240%

    No Known Activations