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

    Neuronpedia

    INDEX
    Explanations

    ASCII art patterns and formats

    oai_token-act-pair · gpt-3.5-turbo

    symbols and special characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     agre
    -0.66
     princ
    -0.63
    anwhile
    -0.59
    conservancy
    -0.58
     psychiat
    -0.57
     occas
    -0.56
    oulos
    -0.56
     conclud
    -0.56
     confir
    -0.56
     undermin
    -0.53
    POSITIVE LOGITS
    É
    0.68
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    0.68
     ||
    0.60
    -|
    0.59
    âĢ¦âĢ¦
    0.59
    __
    0.57
    ~~~~
    0.57
    ___
    0.56
     istg
    0.56
    ||
    0.55
    Act Density 0.433%

    No Known Activations