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

    Neuronpedia

    INDEX
    Explanations

    the word "expectations"

    oai_token-act-pair · gpt-3.5-turbo

    references to expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ston
    -0.81
    packing
    -0.78
    ole
    -0.74
    mans
    -0.69
    phys
    -0.66
    stocks
    -0.65
    cise
    -0.65
    fed
    -0.65
    Interstitial
    -0.64
    nan
    -0.64
    POSITIVE LOGITS
     expectations
    1.03
     expectation
    0.86
    omething
    0.74
    urity
    0.70
    ÃįÃį
    0.67
     arise
    0.67
    ilitary
    0.64
     thresholds
    0.64
     fulfil
    0.63
    ocious
    0.63
    Act Density 0.017%

    No Known Activations