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

    Neuronpedia

    INDEX
    Explanations

    phrases or words enclosed in quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically periods at the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     metic
    -0.88
    ©¶æ
    -0.84
    wagen
    -0.82
    thur
    -0.79
    cha
    -0.76
    istries
    -0.73
    heed
    -0.73
     lifes
    -0.73
    packed
    -0.69
     expended
    -0.69
    POSITIVE LOGITS
    tumblr
    0.80
    >>\
    0.80
     Boone
    0.79
     Again
    0.78
    /"
    0.77
     fixme
    0.77
     Bezos
    0.75
    icago
    0.75
     Seems
    0.73
     Explain
    0.72
    Act Density 0.082%

    No Known Activations