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

    Neuronpedia

    INDEX
    Explanations

    dates specified in text

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "in" used in various contexts, particularly related to time or location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĺħ
    -0.69
    xiety
    -0.63
    Plot
    -0.62
    uthor
    -0.61
    lain
    -0.61
    erness
    -0.60
    arming
    -0.58
    hammad
    -0.58
    irs
    -0.58
    NetMessage
    -0.57
    POSITIVE LOGITS
     adolesc
    0.77
    ixties
    0.75
     2003
    0.75
     2004
    0.73
     2005
    0.72
     1985
    0.71
     1990
    0.70
     2007
    0.70
     1986
    0.69
     1987
    0.68
    Act Density 0.073%

    No Known Activations