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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technology and software

    oai_token-act-pair · gpt-3.5-turbo

    special characters or non-alphanumeric symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erest
    -0.69
    iple
    -0.69
    orts
    -0.68
    pped
    -0.64
    ji
    -0.64
    ega
    -0.63
    pex
    -0.62
    ija
    -0.62
     level
    -0.61
    zhou
    -0.61
    POSITIVE LOGITS
     namely
    1.21
    perhaps
    1.19
    albeit
    1.16
    especially
    1.05
    particularly
    1.01
    something
    1.00
    ————
    0.99
    even
    0.97
     albeit
    0.96
    whether
    0.95
    Act Density 0.161%

    No Known Activations