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

    Neuronpedia

    INDEX
    Explanations

    social etiquette and behavior in dining contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.70
     betweenstory
    -0.61
    oredCriteria
    -0.59
     <>",
    -0.58
    Y
    -0.47
    *
    -0.45
    ↵
    -0.43
     Roskov
    -0.41
    White
    -0.41
    (
    -0.41
    POSITIVE LOGITS
    dhury
    0.84
     surla
    0.78
    WriteLiteral
    0.69
    astéro
    0.69
    ividual
    0.67
    frastructure
    0.66
     AssemblyVersion
    0.65
    jectures
    0.65
    pection
    0.65
    endaten
    0.65
    Act Density 0.545%

    No Known Activations