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

    Neuronpedia

    INDEX
    Explanations

    references to specific values or amounts

    oai_token-act-pair · gpt-3.5-turbo

    the token representing the end of text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     campaigned
    -0.55
     Niet
    -0.53
     tooth
    -0.51
     Seym
    -0.51
     vulner
    -0.51
     precious
    -0.50
     coupled
    -0.50
     apart
    -0.49
    calling
    -0.49
     nationally
    -0.49
    POSITIVE LOGITS
    ggles
    1.25
    ilet
    1.04
    pload
    1.01
    wered
    0.98
    pless
    0.92
    dos
    0.90
     denote
    0.89
    ffee
    0.88
    othy
    0.87
    asts
    0.87
    Act Density 0.051%

    No Known Activations