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

    Neuronpedia

    INDEX
    Explanations

    repetitive patterns of words ending with 'ta'

    oai_token-act-pair · gpt-3.5-turbo

    the repeated phrase "ta", which may indicate a focus on some specific balanced or normalized statistical metric

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     depreciation
    -0.61
     hybrid
    -0.60
     readable
    -0.59
     peril
    -0.57
     Junk
    -0.57
     disaster
    -0.57
    vernment
    -0.56
     Remastered
    -0.55
     Pages
    -0.54
     Lethal
    -0.54
    POSITIVE LOGITS
    ta
    4.58
    tan
    1.96
    ti
    1.70
    tes
    1.49
    tta
    1.40
    tin
    1.39
    tar
    1.38
    tis
    1.30
    TA
    1.30
    ts
    1.28
    Act Density 0.017%

    No Known Activations