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

    Neuronpedia

    INDEX
    Explanations

    years or dates

    oai_token-act-pair · gpt-3.5-turbo

    recurring years and dates associated with historical events or milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     snipp
    -0.69
    IPP
    -0.64
     Jugg
    -0.64
    Jackson
    -0.62
     pse
    -0.61
    ACTION
    -0.60
    Dialogue
    -0.59
    JP
    -0.57
    Throw
    -0.56
     Sym
    -0.56
    POSITIVE LOGITS
     onwards
    0.83
    ties
    0.74
    cards
    0.73
     onward
    0.71
    âĢ²
    0.70
    rf
    0.68
    quist
    0.65
    chel
    0.65
    mable
    0.64
    escent
    0.63
    Act Density 0.104%

    No Known Activations