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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "of"

    oai_token-act-pair · gpt-3.5-turbo

    references to episodes in a series or show

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anders
    -0.89
    ghan
    -0.87
    ayers
    -0.75
    ibling
    -0.74
    anchester
    -0.73
    tymology
    -0.73
    ocene
    -0.72
    izabeth
    -0.70
     teasp
    -0.70
    osaurus
    -0.69
    POSITIVE LOGITS
     Episode
    0.79
     Flip
    0.75
     Omni
    0.72
     ABC
    0.71
     Operation
    0.71
     Premiere
    0.70
     Notting
    0.70
     RELE
    0.70
     Closed
    0.70
     Nationwide
    0.68
    Act Density 0.152%

    No Known Activations