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

    Neuronpedia

    INDEX
    Explanations

    financial and numerical information

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and phrases related to financial magnitude and implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     introdu
    -0.63
     [|
    -0.60
     obser
    -0.58
     corrections
    -0.58
     warr
    -0.57
     saf
    -0.57
     awhile
    -0.56
     horizont
    -0.56
     refinement
    -0.56
     stumble
    -0.56
    POSITIVE LOGITS
    population
    0.75
    osate
    0.75
    ousands
    0.72
    undreds
    0.65
    aughtered
    0.64
    ihadi
    0.61
    valued
    0.60
    efully
    0.60
    oxic
    0.59
    oplan
    0.59
    Act Density 0.925%

    No Known Activations