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

    Neuronpedia

    INDEX
    Explanations

    names of famous philosophers

    oai_token-act-pair · gpt-3.5-turbo

    references to classical philosophers and their works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hips
    -0.74
     ramps
    -0.74
    eals
    -0.74
    AMI
    -0.73
    DAQ
    -0.71
    cream
    -0.69
    ULTS
    -0.66
    vals
    -0.65
    thening
    -0.64
    secut
    -0.64
    POSITIVE LOGITS
     Aristotle
    0.91
    sonian
    0.88
     Dante
    0.86
     Socrates
    0.86
     Hume
    0.86
     Kant
    0.86
    onom
    0.84
     Plato
    0.83
     philosopher
    0.82
     Browne
    0.80
    Act Density 0.022%

    No Known Activations