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

    Neuronpedia

    INDEX
    Explanations

    numeric values preceded by a dollar sign

    oai_token-act-pair · gpt-3.5-turbo

    financial discussions or statements about costs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     neighbourhoods
    -0.77
     neighbourhood
    -0.77
     achie
    -0.75
     landsl
    -0.68
     villages
    -0.67
     pensions
    -0.67
     ageing
    -0.67
     strugg
    -0.67
     supermarkets
    -0.66
     destro
    -0.66
    POSITIVE LOGITS
    Apparently
    1.30
    He
    1.24
    Huh
    1.24
    His
    1.19
    Asked
    1.17
    Again
    1.15
    Anyway
    1.15
    Hmm
    1.12
    Later
    1.11
    Actually
    1.11
    Act Density 0.713%

    No Known Activations