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

    Neuronpedia

    INDEX
    Explanations

    names of geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    references to the character "Beau" and related names in the context of a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izoph
    -0.74
    wagen
    -0.74
    alling
    -0.74
     Lanka
    -0.73
     compr
    -0.72
    ´
    -0.71
    loo
    -0.70
     carniv
    -0.69
    medi
    -0.68
    amera
    -0.68
    POSITIVE LOGITS
    INESS
    0.99
    dylib
    0.77
    hem
    0.76
    bsite
    0.75
    wright
    0.74
     Foley
    0.72
    ESH
    0.72
    kson
    0.71
    heit
    0.71
    AMD
    0.70
    Act Density 0.023%

    No Known Activations