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

    Neuronpedia

    INDEX
    Explanations

    ranges of numerical values

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate numerical ranges or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.75
    dain
    -0.70
     ALWAYS
    -0.70
    ISA
    -0.70
    >>>>>>>>
    -0.67
    rod
    -0.66
    Characters
    -0.65
    umps
    -0.64
    BUG
    -0.63
    ATA
    -0.63
    POSITIVE LOGITS
     30
    0.71
     35
    0.69
     20
    0.69
     60
    0.68
     90
    0.67
     10
    0.67
     2025
    0.65
     40
    0.65
     18
    0.65
     1830
    0.64
    Act Density 0.042%

    No Known Activations