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

    Neuronpedia

    INDEX
    Explanations

    numbers preceded by '95'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the number 95 in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Newsletter
    -0.77
    ulet
    -0.70
    :{
    -0.70
    nir
    -0.66
    advertising
    -0.66
    gallery
    -0.65
    UM
    -0.63
    Entry
    -0.62
    gey
    -0.61
    ous
    -0.60
    POSITIVE LOGITS
     95
    3.25
     97
    2.38
     98
    2.31
     94
    2.25
     96
    2.23
     93
    2.17
     99
    2.16
     92
    2.03
     85
    1.99
     91
    1.93
    Act Density 0.024%

    No Known Activations