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

    Neuronpedia

    INDEX
    Explanations

    metaphors and metaphorical language

    oai_token-act-pair · gpt-3.5-turbo

    references to metaphors and analogies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ierra
    -0.74
     Citiz
    -0.72
    selection
    -0.67
    oway
    -0.67
    guards
    -0.66
    avorite
    -0.65
    Lago
    -0.65
    emale
    -0.64
    astered
    -0.64
    ovo
    -0.63
    POSITIVE LOGITS
     metaphor
    0.85
    ically
    0.84
     metaphors
    0.77
    izon
    0.73
     analogy
    0.71
    gdala
    0.70
    rast
    0.69
     wink
    0.69
     drowning
    0.69
    hemer
    0.69
    Act Density 0.049%

    No Known Activations