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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and concepts

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

    programming code and technical syntax elements.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     Houſe
    -0.58
    Royce
    -0.56
     ujednoznacz
    -0.56
     Nirvana
    -0.54
    ьаж
    -0.54
    terre
    -0.53
     ModelExpression
    -0.53
    Hentet
    -0.53
    IVEREF
    -0.51
    figcaption
    -0.50
    POSITIVE LOGITS
     character
    1.16
     characters
    1.14
     letter
    1.02
     letters
    0.98
    characters
    0.97
    character
    0.96
     Character
    0.96
    Character
    0.93
     Characters
    0.93
     char
    0.87
    Act Density 0.457%

    No Known Activations