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

    Neuronpedia

    INDEX
    Explanations

    instances where the concept of something being present or happening is discussed alongside the need for a specific action or response

    oai_token-act-pair · gpt-3.5-turbo

    references to quantities or amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arta
    -0.74
    Squ
    -0.71
     Dreams
    -0.70
    buck
    -0.68
     Values
    -0.63
    _-
    -0.62
     wisely
    -0.61
    values
    -0.60
    olds
    -0.60
     sucks
    -0.60
    POSITIVE LOGITS
     outcry
    1.16
     shortage
    1.16
     uproar
    1.05
     backlash
    0.95
     discrepancy
    0.95
     mismatch
    0.89
     noticeable
    0.86
     interruption
    0.85
     reaction
    0.85
     chance
    0.83
    Act Density 0.244%

    No Known Activations