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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to statistical testing and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     high
    -0.84
     low
    -0.76
     higher
    -0.71
     minor
    -0.71
     modern
    -0.71
     small
    -0.71
     global
    -0.71
     basic
    -0.70
     major
    -0.69
     primary
    -0.69
    POSITIVE LOGITS
    +#+
    0.57
    ukone
    0.53
    :✨
    0.53
     artísticas
    0.50
    ftrag
    0.48
    chnen
    0.46
    IndentedString
    0.45
     Exacts
    0.45
    genheiten
    0.44
    \{\\
    0.44
    Act Density 1.011%

    No Known Activations