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

    Neuronpedia

    INDEX
    Explanations

    names of authors and book titles with years

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and their associated works, particularly in an academic or publication context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    netflix
    -0.75
    canon
    -0.70
    itiz
    -0.65
    LAB
    -0.64
    daq
    -0.61
     chanted
    -0.60
     blur
    -0.59
    justice
    -0.58
    fell
    -0.58
    offset
    -0.58
    POSITIVE LOGITS
     et
    0.85
     Handbook
    0.84
    .,
    0.82
     Jr
    0.80
     Identification
    0.78
     Encyclopedia
    0.77
    .;
    0.74
     Proceedings
    0.71
     Functional
    0.71
    .:
    0.66
    Act Density 0.119%

    No Known Activations