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

    Neuronpedia

    INDEX
    Explanations

    instances that indicate progression, continuation, or advancement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "further" indicating progression or additional information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eve
    -0.88
    cius
    -0.73
    eyes
    -0.71
    eye
    -0.69
    Hey
    -0.63
     hey
    -0.62
    zech
    -0.62
     Solitaire
    -0.62
    type
    -0.61
    Favorite
    -0.61
    POSITIVE LOGITS
     further
    3.52
     farther
    1.97
     Further
    1.87
    Further
    1.86
    urther
    1.83
     deeper
    1.45
     furthe
    1.43
     additional
    1.36
     closer
    1.28
     additionally
    1.28
    Act Density 0.025%

    No Known Activations