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

    Neuronpedia

    INDEX
    Explanations

    specific instances where something is almost but not quite achieved or eliminated

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey a sense of concession or contrast

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alion
    -0.67
    Synopsis
    -0.65
     Amph
    -0.64
    pta
    -0.60
     concess
    -0.60
    agra
    -0.58
     Dynamic
    -0.58
     ze
    -0.58
    dayName
    -0.58
    omics
    -0.57
    POSITIVE LOGITS
    UF
    0.66
    USS
    0.63
    tg
    0.63
     succumbed
    0.62
    tered
    0.62
    theless
    0.61
    riel
    0.61
     Kern
    0.61
    uke
    0.60
    fur
    0.60
    Act Density 0.019%

    No Known Activations