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

    Neuronpedia

    INDEX
    Explanations

    mentions of physical or metaphorical journeys

    oai_token-act-pair · gpt-3.5-turbo

    references to personal journeys or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ioch
    -0.71
     harmless
    -0.66
    zona
    -0.66
    erva
    -0.66
    essee
    -0.65
    ividual
    -0.64
     nit
    -0.64
    encies
    -0.63
     atoms
    -0.63
    uctor
    -0.62
    POSITIVE LOGITS
    è£ħ
    0.95
    wright
    0.93
     Journey
    0.90
    icular
    0.88
    ogue
    0.84
    naire
    0.82
     Trave
    0.81
     voyage
    0.80
    neys
    0.76
     Archdemon
    0.76
    Act Density 0.020%

    No Known Activations