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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating logic, rationality, or coherence

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     ?...
    -1.05
     emphat
    -1.05
     !...
    -0.93
     immen
    -0.92
     increa
    -0.92
     accla
    -0.90
     alre
    -0.90
     tantôt
    -0.90
     guarante
    -0.89
     Augu
    -0.89
    POSITIVE LOGITS
     sense
    0.98
    sense
    0.84
     Sense
    0.78
    ensical
    0.78
     SENSE
    0.72
    Sense
    0.69
     sentido
    0.65
     sens
    0.61
    fony
    0.59
     logic
    0.57
    Act Density 0.064%

    No Known Activations