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

    Neuronpedia

    INDEX
    Explanations

    locations or places near a specified point of interest

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize proximity or closeness to a specific location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    manship
    -0.78
     wisely
    -0.76
     aloud
    -0.71
     namely
    -0.71
     alone
    -0.68
    fully
    -0.68
     beforehand
    -0.67
     according
    -0.67
     however
    -0.66
    PLIC
    -0.65
    POSITIVE LOGITS
     same
    1.08
     periphery
    1.08
     horizon
    1.01
     edges
    1.00
     confines
    0.99
     outskirts
    0.95
     proverbial
    0.95
     nearest
    0.93
     smallest
    0.92
     entrance
    0.91
    Act Density 0.333%

    No Known Activations