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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating decision-making or actions that go beyond what is necessary

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "So" signaling a transition or conclusion in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    taboola
    -0.66
    "},"
    -0.65
    saf
    -0.64
    capt
    -0.62
    thro
    -0.62
    mast
    -0.59
    iqueness
    -0.59
     neighb
    -0.59
     obstacle
    -0.57
    "],"
    -0.57
    POSITIVE LOGITS
    bered
    1.12
    ooo
    1.01
    oner
    1.01
    oooo
    0.99
     yeah
    0.96
    fter
    0.90
    aring
    0.89
    apy
    0.88
    oths
    0.88
     whats
    0.87
    Act Density 0.057%

    No Known Activations