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

    Neuronpedia

    INDEX
    Explanations

    phrases related to self-awareness and reflection

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character "Ļ" in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mobil
    -0.59
     Skydragon
    -0.59
     Gaul
    -0.57
     Polk
    -0.57
     Azerb
    -0.55
     Kurdistan
    -0.55
     fragmentation
    -0.54
     Palestin
    -0.54
     Rhodes
    -0.54
     metic
    -0.53
    POSITIVE LOGITS
    s
    1.19
    t
    1.03
    scl
    0.94
    ll
    0.93
    sure
    0.93
    sent
    0.91
    tis
    0.90
    ski
    0.89
    mean
    0.87
    sed
    0.85
    Act Density 0.259%

    No Known Activations