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

    Neuronpedia

    INDEX
    Explanations

    phrases related to historical events or significant occurrences

    oai_token-act-pair · gpt-3.5-turbo

    the term "Great" associated with historical events or periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.83
    ograp
    -0.80
    isSpecialOrderable
    -0.80
    qqa
    -0.80
    earchers
    -0.79
    utical
    -0.76
    clips
    -0.74
    bec
    -0.74
    ople
    -0.74
    uably
    -0.71
    POSITIVE LOGITS
    batch
    0.90
     Lakes
    0.87
     Basin
    0.86
     Recession
    0.84
    ness
    0.81
     Barrier
    0.79
     Divide
    0.78
     strides
    0.76
     Depression
    0.74
     Plains
    0.74
    Act Density 0.015%

    No Known Activations