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

    Neuronpedia

    INDEX
    Explanations

    Miscellaneous items and collections of related things

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating selection or aggregation of items or people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aeus
    -0.77
    imeter
    -0.74
    ared
    -0.72
    erate
    -0.71
    Reviewer
    -0.70
    ocene
    -0.70
    rome
    -0.67
    ipeg
    -0.66
    uca
    -0.66
    agall
    -0.64
    POSITIVE LOGITS
     goodies
    1.16
     assorted
    0.96
     items
    0.95
     notable
    0.91
     highlights
    0.91
     articles
    0.88
     extras
    0.88
     celebrities
    0.87
     appearances
    0.84
    cellaneous
    0.83
    Act Density 0.334%

    No Known Activations