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

    Neuronpedia

    INDEX
    Explanations

    negative numerical references or codes related to statistics and data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UnknownFields
    -0.71
    glEnd
    -0.68
     CONDITIONS
    -0.65
     OnTrigger
    -0.65
    AsUp
    -0.64
    ']").
    -0.64
    pulumi
    -0.61
    riwal
    -0.60
     ters
    -0.60
    "]').
    -0.59
    POSITIVE LOGITS
     natale
    0.72
     atve
    0.71
     isolado
    0.68
    TagMode
    0.67
     year
    0.65
     popolare
    0.64
     miliardi
    0.63
    Year
    0.62
     fratelli
    0.62
     onwards
    0.62
    Act Density 0.084%

    No Known Activations