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

    Neuronpedia

    INDEX
    Explanations

    descriptions of personal experiences and reflections

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     balon
    -0.78
     rú
    -0.73
     parlamento
    -0.73
     utop
    -0.71
     meras
    -0.70
     kön
    -0.70
     pavo
    -0.70
     torba
    -0.68
    StructEnd
    -0.67
     karton
    -0.66
    POSITIVE LOGITS
     maintained
    0.48
     alternating
    0.47
     kept
    0.46
     montr
    0.45
    lüğü
    0.45
    Keeps
    0.44
    jusqu
    0.43
    moteur
    0.43
     held
    0.43
     keep
    0.43
    Act Density 0.324%

    No Known Activations