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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "peak"

    oai_token-act-pair · gpt-3.5-turbo

    references to maximum levels or peaks in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icate
    -0.75
    oured
    -0.74
    ktop
    -0.73
    signed
    -0.72
    erie
    -0.69
    cheat
    -0.69
    onsense
    -0.67
     parted
    -0.66
     Cosponsors
    -0.66
    recated
    -0.66
    POSITIVE LOGITS
     erection
    0.77
     peaks
    0.73
    urb
    0.73
     heights
    0.72
    lite
    0.71
     height
    0.71
    ceed
    0.69
     occupancy
    0.69
     capacity
    0.69
    imum
    0.69
    Act Density 0.019%

    No Known Activations