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

    Neuronpedia

    INDEX
    Explanations

    presence of a specific format or structure in code, particularly patterns of output or return values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    διά
    -0.53
     maternelle
    -0.52
    Blanc
    -0.51
    Süd
    -0.50
     TTT
    -0.50
    -0.49
     interest
    -0.48
     personnalité
    -0.47
    hors
    -0.47
    brain
    -0.47
    POSITIVE LOGITS
     AssemblyCulture
    0.85
    else
    0.85
    GOTREF
    0.77
     else
    0.77
    RetentionPolicy
    0.74
     تضيفلها
    0.69
    enumi
    0.69
    '||
    0.66
    HasAnnotation
    0.66
    elseif
    0.65
    Act Density 0.062%

    No Known Activations