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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases indicating something is superior

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize comparative statements or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esome
    -0.80
    swick
    -0.78
    ysc
    -0.73
    idon
    -0.73
    pta
    -0.71
    ovie
    -0.71
    İĭ
    -0.70
    ogens
    -0.70
    agate
    -0.70
    ologies
    -0.68
    POSITIVE LOGITS
     appreciated
    0.91
     simpler
    0.85
     ado
    0.79
     nicer
    0.75
    NESS
    0.74
     esteemed
    0.72
     easier
    0.71
     fun
    0.69
     enough
    0.69
     respected
    0.68
    Act Density 0.035%

    No Known Activations