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

    Neuronpedia

    INDEX
    Explanations

    numbers that are part of a sequence

    oai_token-act-pair · gpt-3.5-turbo

    numeric values and elements related to separation and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Chili
    -0.85
    cel
    -0.78
    Brit
    -0.75
     367
    -0.73
     369
    -0.73
     275
    -0.72
     366
    -0.71
     370
    -0.71
     Helic
    -0.70
    kel
    -0.70
    POSITIVE LOGITS
     out
    1.50
     OUT
    1.36
    out
    1.32
     outs
    1.32
    OUT
    1.26
     Out
    1.25
    Out
    1.17
    outs
    1.15
     Outs
    1.03
     forth
    0.91
    Act Density 0.193%

    No Known Activations