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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a sense of awareness or understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    könyv
    -0.73
     Alvarado
    -0.72
     Carvalho
    -0.72
    upaten
    -0.67
     smtplib
    -0.67
     Kidman
    -0.67
    rawler
    -0.67
    chnung
    -0.67
    Zeneca
    -0.66
     unsuccessful
    -0.66
    POSITIVE LOGITS
     SENSE
    1.90
     Sense
    1.81
     sense
    1.73
    Sense
    1.63
    sense
    1.60
     senses
    1.52
     Senses
    1.30
     sensed
    1.30
     senso
    1.15
     sensing
    1.14
    Act Density 0.083%

    No Known Activations