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

    Neuronpedia

    INDEX
    Explanations

    syntax and structure related to programming and policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    絡
    -0.15
    à¥įयप
    -0.14
    irk
    -0.14
    ÑĢÑĸй
    -0.13
     sno
    -0.13
     Sanford
    -0.13
    모
    -0.13
    zone
    -0.13
     tits
    -0.13
    ular
    -0.13
    POSITIVE LOGITS
     statement
    0.92
    statement
    0.80
     Statement
    0.77
     statements
    0.75
    Statement
    0.73
    _statement
    0.70
     Statements
    0.66
    statements
    0.66
     stat
    0.66
    -stat
    0.60
    Act Density 0.086%

    No Known Activations