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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by a decimal point

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical values, particularly those expressed in a financial context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     shopping
    -0.68
     traveled
    -0.65
     travelling
    -0.63
     bunny
    -0.61
     buyer
    -0.61
     travelled
    -0.59
     traveling
    -0.59
     spread
    -0.58
     whipped
    -0.58
     sworn
    -0.57
    POSITIVE LOGITS
    307
    0.89
    wm
    0.85
    662
    0.84
    284
    0.83
    659
    0.83
    396
    0.82
    285
    0.82
    42
    0.82
    309
    0.81
    409
    0.81
    Act Density 0.174%

    No Known Activations