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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and notations used in formal proofs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -0.58
    migrationBuilder
    -0.57
     
    -0.48
    ↵↵↵
    -0.47
    naden
    -0.45
    ↵
    -0.45
     {
    -0.45
     So
    -0.43
    ).
    -0.43
    stal
    -0.43
    POSITIVE LOGITS
    IVEREF
    0.86
    SBATCH
    0.82
     FetchType
    0.72
    poptosis
    0.72
    انيف
    0.71
    extAlignment
    0.70
    Personensuche
    0.69
    SourceChecksum
    0.69
     whoſe
    0.69
     lópez
    0.67
    Act Density 1.746%

    No Known Activations