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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating procedural steps or actions involving systems and their management

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

    new access position opportunity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused28>
    -1.11
    <unused8>
    -1.11
    <unused68>
    -1.11
    <unused79>
    -1.11
    <unused43>
    -1.11
    <unused52>
    -1.11
    <unused14>
    -1.10
    <unused16>
    -1.10
    <unused3>
    -1.10
    [@BOS@]
    -1.10
    POSITIVE LOGITS
    ,
    0.50
    ://
    0.41
     -
    0.40
    .
    0.40
     (
    0.39
    ;
    0.38
    ↵↵
    0.37
    -
    0.37
     
    0.37
     /
    0.36
    Act Density 0.243%

    No Known Activations