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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to data structures and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by periods, semicolons, or parentheses

    np_acts-logits-general · gemini-2.0-flash

    punctuation after words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ^(@)
    -0.96
     Forumite
    -0.93
    ՚
    -0.93
     Efq
    -0.93
     Majefty
    -0.93
    ſelves
    -0.93
    _
    -0.90
     myſelf
    -0.90
    ſelf
    -0.90
     itſelf
    -0.90
    POSITIVE LOGITS
    .
    0.81
    ;
    0.70
    <eos>
    0.63
    ValueStyle
    0.57
    )
    0.56
     but
    0.56
    ).
    0.55
    ,
    0.54
     (
    0.54
    ...
    0.54
    Act Density 0.443%

    No Known Activations