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

    Neuronpedia

    INDEX
    Explanations

    numbers separated by a hyphen within a sentence or phrase

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and their relationships in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shutterstock
    -0.85
     Somalia
    -0.74
     Purs
    -0.72
     Reporting
    -0.70
     Debor
    -0.68
     Leilan
    -0.68
     Athletics
    -0.67
     Bernstein
    -0.66
     Photographer
    -0.63
    terday
    -0.61
    POSITIVE LOGITS
    Ps
    0.83
    western
    0.82
    isen
    0.78
    adult
    0.78
    alties
    0.78
    ilers
    0.77
    andals
    0.77
    Ms
    0.76
    heastern
    0.76
    casts
    0.75
    Act Density 0.328%

    No Known Activations