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

    Neuronpedia

    INDEX
    Explanations

    quotations at the end of sentences

    oai_token-act-pair · gpt-3.5-turbo

    concluding sentences or statements that signify the end of a thought

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     numer
    -0.71
     staggered
    -0.70
    ptin
    -0.69
     coerc
    -0.68
    umeric
    -0.65
     overloaded
    -0.65
    atts
    -0.64
    ¾
    -0.64
    acco
    -0.63
    ength
    -0.61
    POSITIVE LOGITS
     âĢķ
    0.97
     Said
    0.88
     Asked
    0.75
     Huh
    0.74
     Speak
    0.74
     Translation
    0.72
     Saying
    0.72
     Adds
    0.71
    said
    0.70
     Hearing
    0.70
    Act Density 0.113%

    No Known Activations