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

    Neuronpedia

    INDEX
    Explanations

    dates and figures in a financial context

    oai_token-act-pair · gpt-3.5-turbo

    expressions of cautious or negative advice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     polio
    -0.65
     missing
    -0.58
     red
    -0.56
     inadvert
    -0.56
     shining
    -0.55
     simultane
    -0.55
     miscarriage
    -0.55
     permissible
    -0.55
     failure
    -0.55
     closest
    -0.54
    POSITIVE LOGITS
    ution
    1.03
    cies
    0.92
    ship
    0.90
    ues
    0.90
    ulty
    0.90
    utive
    0.89
    hips
    0.88
    ationally
    0.88
    ember
    0.88
    igious
    0.87
    Act Density 0.178%

    No Known Activations