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

    Neuronpedia

    INDEX
    Explanations

    references to high points or peaks

    oai_token-act-pair · gpt-3.5-turbo

    references to levels or maxima of various metrics or phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oured
    -0.74
    signed
    -0.70
     transpl
    -0.69
    cheat
    -0.67
    harm
    -0.66
    icate
    -0.66
    erie
    -0.66
    onsense
    -0.65
    icator
    -0.65
    YA
    -0.64
    POSITIVE LOGITS
     peaks
    0.85
     peak
    0.82
     heights
    0.80
     height
    0.78
     highs
    0.77
     erection
    0.76
     lows
    0.72
     earners
    0.71
    phrine
    0.70
     pinnacle
    0.68
    Act Density 0.007%

    No Known Activations