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

    Neuronpedia

    INDEX
    Explanations

    information about the age of articles, including relevant details

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "this article is" followed by various descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Temper
    -0.71
     Telesc
    -0.66
    undreds
    -0.65
     Towers
    -0.64
    ths
    -0.62
    Laughs
    -0.62
    gom
    -0.62
    Others
    -0.62
    iever
    -0.61
    uctor
    -0.60
    POSITIVE LOGITS
     unlikely
    0.76
     NOT
    0.76
     important
    0.76
     also
    0.76
     definitely
    0.75
     archived
    0.75
     updated
    0.74
     not
    0.73
     extremely
    0.73
     likely
    0.72
    Act Density 0.181%

    No Known Activations