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

    Neuronpedia

    INDEX
    Explanations

    numbers within a sentence

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "more than" followed by numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ESA
    -0.63
    tto
    -0.62
     Duo
    -0.58
     bedrock
    -0.57
     Blazers
    -0.56
    Wr
    -0.55
     wellbeing
    -0.55
    =/
    -0.55
    ãĤ¦ãĤ¹
    -0.54
    ngth
    -0.54
    POSITIVE LOGITS
    000
    1.02
    ousand
    1.02
    700
    0.87
    00
    0.85
     000
    0.83
    500
    0.81
    800
    0.78
    600
    0.77
    dozen
    0.76
    300
    0.74
    Act Density 0.083%

    No Known Activations