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

    Neuronpedia

    INDEX
    Explanations

    specific instructions or information indicated by phrases like "How to Apply," "ad scans for accuracy," "filter data," and "select survey questions."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" and variations indicating referral or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anooga
    -0.70
    zon
    -0.69
     thereof
    -0.67
    unta
    -0.65
    iac
    -0.63
    ifer
    -0.62
     such
    -0.62
     suppose
    -0.62
     tending
    -0.62
     portraying
    -0.61
    POSITIVE LOGITS
     latest
    1.20
     aforementioned
    1.06
     entirety
    1.05
     entire
    1.01
     following
    1.01
     respective
    0.98
     widest
    0.96
     latter
    0.95
     rest
    0.94
     nearest
    0.94
    Act Density 0.284%

    No Known Activations