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

    Neuronpedia

    INDEX
    Explanations

    phrases related to procedural language and legal context

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

    Follows a determiner or preposition

    np_acts-logits-general · gemini-2.0-flash

    punctuation and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ་་
    -1.17
    etheless
    -1.11
     ―――――
    -1.06
    ^(@)
    -1.05
     $_"
    -1.04
    ſelves
    -1.02
    >\<^
    -1.01
    NUMX
    -1.01
    \<^
    -0.99
    ressee
    -0.98
    POSITIVE LOGITS
    <eos>
    1.16
    ↵↵
    1.05
    !
    0.95
    ↵↵↵
    0.93
    ↵
    0.92
    .
    0.91
    :
    0.88
    ...
    0.88
    ?
    0.87
    ..
    0.85
    Act Density 1.315%

    No Known Activations