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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "ang"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of orangutans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pwr
    -0.78
     isot
    -0.74
     Seym
    -0.73
    nesday
    -0.72
    merga
    -0.72
    earcher
    -0.68
    everal
    -0.65
    ngth
    -0.65
    ouple
    -0.65
     electroly
    -0.65
    POSITIVE LOGITS
    aroo
    1.14
    ang
    1.03
    angs
    1.00
    etsu
    1.00
    lia
    0.86
    bang
    0.85
    lers
    0.83
    ethe
    0.83
    yang
    0.83
    gang
    0.79
    Act Density 0.013%

    No Known Activations