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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "switch" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    za
    -0.79
    kamp
    -0.69
    icist
    -0.68
    icone
    -0.66
    von
    -0.62
    raq
    -0.61
    nutrition
    -0.61
    76561
    -0.61
    zza
    -0.60
    cision
    -0.59
    POSITIVE LOGITS
     gears
    0.97
    blade
    0.87
     between
    0.86
     alleg
    0.84
    nil
    0.83
     genders
    0.83
     switches
    0.82
     lanes
    0.82
     switch
    0.81
     seamlessly
    0.81
    Act Density 0.015%

    No Known Activations