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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparative evaluations or distinctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GrantedAuthority
    -0.69
    abestanden
    -0.67
    windowFixed
    -0.67
    expandindo
    -0.63
    ENODEV
    -0.58
    rrggbb
    -0.56
    !*\
    -0.55
    providedIn
    -0.55
     дописавши
    -0.54
    Datuak
    -0.52
    POSITIVE LOGITS
     actual
    0.65
    Actual
    0.59
     Actual
    0.59
    ographi
    0.58
     official
    0.56
    actual
    0.56
     eigentlichen
    0.55
     Formal
    0.55
    具体
    0.55
     ursprünglich
    0.55
    Act Density 0.456%

    No Known Activations