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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating progress or advancement

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "get on" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    APD
    -0.63
     omission
    -0.63
    LY
    -0.60
     Bulg
    -0.58
    Missing
    -0.57
    Mand
    -0.56
     subdu
    -0.56
     foss
    -0.55
    WARE
    -0.55
    Interstitial
    -0.55
    POSITIVE LOGITS
    entary
    0.79
     traction
    0.75
     foothold
    0.75
    ossip
    0.73
    itiveness
    0.71
    abit
    0.71
    started
    0.69
    retty
    0.69
    ophobic
    0.67
    isson
    0.66
    Act Density 0.063%

    No Known Activations