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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    the definite article "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     besides
    -0.73
    âĢł
    -0.72
    leeve
    -0.71
    AMA
    -0.69
    IFA
    -0.66
    wash
    -0.65
    Tier
    -0.64
    elaide
    -0.64
    MU
    -0.64
    asonry
    -0.63
    POSITIVE LOGITS
     slightest
    1.20
     smallest
    1.18
     entirety
    1.14
     usual
    1.13
     same
    1.13
     latter
    1.12
     entire
    1.12
     aforementioned
    1.10
     vast
    1.06
     remainder
    1.06
    Act Density 0.497%

    No Known Activations