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

    Neuronpedia

    INDEX
    Explanations

    comparative statements indicating an increased degree or level

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing increasing intensity or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gio
    -1.01
    ocene
    -0.80
    esan
    -0.72
    meet
    -0.71
    only
    -0.70
    ences
    -0.66
    cius
    -0.66
    uese
    -0.65
     Rapp
    -0.65
    medium
    -0.64
    POSITIVE LOGITS
     stringent
    0.89
     potent
    0.85
     impressive
    0.83
     ambitious
    0.81
     precarious
    0.78
     challeng
    0.76
     expensive
    0.74
     ardent
    0.74
     than
    0.74
     exciting
    0.74
    Act Density 0.052%

    No Known Activations