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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decreasing or lowering something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ALT
    -0.75
    SPONSORED
    -0.75
     Pascal
    -0.66
    âĢij
    -0.61
    ctl
    -0.61
    NULL
    -0.61
    mate
    -0.60
    /
    -0.60
     Dumbledore
    -0.60
    craft
    -0.59
    POSITIVE LOGITS
     entire
    1.41
     whole
    1.13
     entirety
    1.10
     remainder
    1.08
     slightest
    1.07
     same
    0.98
    ses
    0.97
     latter
    0.96
     proverbial
    0.92
     smallest
    0.91
    Act Density 0.403%

    No Known Activations