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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating authority and official roles within organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.57
    EDEFAULT
    -0.55
    __*/
    -0.49
    UrlResolution
    -0.45
    });*/
    -0.44
     OMITBAD
    -0.44
    Nazionale
    -0.44
     INTERESAR
    -0.42
    Naissance
    -0.42
    MemoryWarning
    -0.41
    POSITIVE LOGITS
     OFDb
    0.45
     kemudian
    0.42
    evos
    0.40
     then
    0.38
     затем
    0.37
     quickly
    0.36
     nurtured
    0.36
     subsequent
    0.35
     later
    0.35
     continues
    0.35
    Act Density 0.623%

    No Known Activations