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

    Neuronpedia

    INDEX
    Explanations

    the word "switch" with a high activation value

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "switch."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    za
    -0.81
    apolis
    -0.72
    ORED
    -0.65
    kamp
    -0.65
    nutrition
    -0.64
    vez
    -0.63
    fare
    -0.62
    USD
    -0.62
    our
    -0.62
    zza
    -0.61
    POSITIVE LOGITS
    blade
    1.02
    grass
    1.01
     switch
    0.89
    aroo
    0.89
    gear
    0.85
    switch
    0.84
    backs
    0.83
     switches
    0.83
     gears
    0.76
    uese
    0.73
    Act Density 0.019%

    No Known Activations