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

    Neuronpedia

    INDEX
    Explanations

    large numbers related to financial transactions

    oai_token-act-pair · gpt-3.5-turbo

    quantities and values related to financial statistics or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rather
    -0.56
     rather
    -0.55
     instead
    -0.52
    $.
    -0.52
    bryce
    -0.51
    ".[
    -0.51
    zi
    -0.50
    )."
    -0.50
    Miami
    -0.50
     ASAP
    -0.49
    POSITIVE LOGITS
     meanwhile
    0.65
     consists
    0.64
     hangs
    0.61
     awaits
    0.58
     consisted
    0.58
     survives
    0.57
     refers
    0.56
     assumes
    0.54
     translates
    0.52
     sprang
    0.52
    Act Density 1.453%

    No Known Activations