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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating certainty or emphasis, such as 'always', 'probably', 'certainly'

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating certainty or continuity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    core
    -0.68
    furt
    -0.67
     Mant
    -0.67
     Respons
    -0.67
    ylum
    -0.66
     Mats
    -0.65
     Mour
    -0.64
    Unity
    -0.62
    Lenin
    -0.61
     Wend
    -0.60
    POSITIVE LOGITS
     afford
    1.08
     withstand
    0.92
     imagine
    0.89
     conceive
    0.88
     communicate
    0.87
    ibly
    0.86
    apply
    0.86
    berra
    0.84
     rely
    0.83
    ivably
    0.83
    Act Density 0.081%

    No Known Activations