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

    Neuronpedia

    INDEX
    Explanations

    various types of ratios and their implications in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gotten
    -0.76
    sylvania
    -0.69
    dream
    -0.69
    pocket
    -0.67
     Ic
    -0.65
    REAM
    -0.65
    uggage
    -0.64
    asper
    -0.64
     concess
    -0.63
    ARK
    -0.62
    POSITIVE LOGITS
    xual
    1.04
     ratios
    0.96
     ratio
    0.87
    yip
    0.83
    ically
    0.80
    nces
    0.79
     mismatch
    0.75
    ical
    0.74
    ally
    0.73
     numer
    0.72
    Act Density 0.006%

    No Known Activations