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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographical locations or bodies of water

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fecture
    -0.74
    âĻ¦
    -0.69
     habitable
    -0.69
     allowable
    -0.68
     unres
    -0.68
     practicable
    -0.66
     recession
    -0.65
    =""
    -0.65
     diffuse
    -0.64
    ivity
    -0.63
    POSITIVE LOGITS
    view
    1.09
    dale
    1.02
    croft
    0.89
    VIEW
    0.88
    finder
    0.87
    walker
    0.86
    wood
    0.86
    hog
    0.86
    fox
    0.85
    hani
    0.84
    Act Density 0.143%

    No Known Activations