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

    Neuronpedia

    INDEX
    Explanations

    punctuation followed by commas in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    「
    -0.76
    ,
    -0.67
    IndentedString
    -0.65
    …
    -0.64
    『
    -0.63
     Baillargeon
    -0.58
    ...
    -0.58
    ContentLoaded
    -0.55
    ."—
    -0.55
     sherds
    -0.54
    POSITIVE LOGITS
     etc
    1.27
     however
    1.19
     but
    1.11
     albeit
    1.07
     which
    1.07
     }}$,
    1.01
     including
    1.00
     namely
    1.00
     though
    0.99
     although
    0.95
    Act Density 2.478%

    No Known Activations