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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or specific phrases related to places or organizations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "The" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.94
     beforehand
    -0.81
    Ò
    -0.76
    iod
    -0.74
     thereby
    -0.74
    /"
    -0.73
    —"
    -0.71
    whatever
    -0.70
    æ©
    -0.70
    .*
    -0.68
    POSITIVE LOGITS
    resa
    1.49
    odore
    1.32
    oret
    1.15
     Latest
    1.08
     latest
    1.01
    ories
    1.01
    atre
    0.94
    orem
    0.91
     biggest
    0.90
     largest
    0.88
    Act Density 0.176%

    No Known Activations