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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political activities or campaigns

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tumblr
    -0.66
     namely
    -0.65
     insofar
    -0.63
     indicating
    -0.63
    hari
    -0.62
     preceded
    -0.61
    utm
    -0.59
    !
    -0.59
     consisting
    -0.57
     Leilan
    -0.57
    POSITIVE LOGITS
     entire
    1.09
     same
    1.08
     remainder
    1.08
     fullest
    1.07
     rest
    1.00
     entirety
    0.99
     slightest
    0.98
    ses
    0.95
     proverbial
    0.95
     whole
    0.91
    Act Density 0.871%

    No Known Activations