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

    Neuronpedia

    INDEX
    Explanations

    phrases related to offering support or endorsement

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "back" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     viz
    -0.69
    ities
    -0.66
    ifix
    -0.65
    rez
    -0.63
    iami
    -0.63
    eria
    -0.59
     Jur
    -0.58
    itsu
    -0.58
     Hots
    -0.58
    uyomi
    -0.57
    POSITIVE LOGITS
    )=(
    1.01
    packs
    1.00
    stab
    0.99
    dated
    0.98
    track
    0.92
    tracking
    0.90
    GROUND
    0.87
    drops
    0.84
    side
    0.84
    stories
    0.83
    Act Density 0.026%

    No Known Activations