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

    Neuronpedia

    INDEX
    Explanations

    phrases related to important matters or issues

    oai_token-act-pair · gpt-3.5-turbo

    references to various topics or issues that are considered significant or noteworthy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    geon
    -0.77
    geons
    -0.69
     largeDownload
    -0.67
    oir
    -0.67
    ades
    -0.66
    oux
    -0.66
    083
    -0.66
    iary
    -0.65
    onz
    -0.63
    ramid
    -0.63
    POSITIVE LOGITS
     happening
    1.18
     happen
    1.15
     happened
    1.01
     happens
    0.88
     pertaining
    0.84
     else
    0.82
     happ
    0.82
     Happ
    0.76
    omething
    0.76
     resembling
    0.75
    Act Density 0.058%

    No Known Activations