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

    Neuronpedia

    INDEX
    Explanations

    statements related to storytelling or narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.98
    「
    -0.80
    …
    -0.79
    ...
    -0.75
    ?
    -0.66
    /
    -0.65
    『
    -0.64
    :
    -0.64
    "
    -0.64
    ."—
    -0.63
    POSITIVE LOGITS
     etc
    1.39
     however
    1.23
     but
    1.19
     albeit
    1.18
     including
    1.12
     which
    1.12
     namely
    1.09
     }}$,
    1.09
     especially
    1.01
     although
    0.98
    Act Density 2.504%

    No Known Activations