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

    Neuronpedia

    INDEX
    Explanations

    time-related expressions indicating a short duration

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a temporal context or duration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anus
    -0.69
    911
    -0.65
    less
    -0.65
    theless
    -0.64
    2020
    -0.63
     Osw
    -0.62
    netflix
    -0.61
    smith
    -0.60
    ukong
    -0.59
    locking
    -0.59
    POSITIVE LOGITS
    ovych
    0.80
    FTWARE
    0.67
    bered
    0.67
    othes
    0.66
    alions
    0.63
    oké
    0.62
     forth
    0.61
     rou
    0.61
    oths
    0.60
    ambers
    0.60
    Act Density 0.014%

    No Known Activations