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

    Neuronpedia

    INDEX
    Explanations

    phrases related to evaluation or judgment

    oai_token-act-pair · gpt-3.5-turbo

    key terms and phrases indicating simplicity or clarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.52
    grand
    -0.51
    ãĥij
    -0.50
    fet
    -0.48
    ãĥĭ
    -0.47
     teasp
    -0.46
    ãĤ¸
    -0.46
    ãĥ¼ãĥ
    -0.45
    pri
    -0.45
    utor
    -0.45
    POSITIVE LOGITS
     ;)
    0.59
     :)
    0.59
     because
    0.53
    !
    0.52
    ;
    0.52
     :-)
    0.51
     when
    0.51
     :(
    0.51
    !!!!!
    0.49
    !,
    0.48
    Act Density 1.725%

    No Known Activations