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

    Neuronpedia

    INDEX
    Explanations

    names of technology companies and individuals working in the tech industry

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and brand names related to electronics and computing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lightly
    -0.55
     starting
    -0.52
     following
    -0.51
     quickly
    -0.50
    âĢİ
    -0.50
     completely
    -0.49
     gradually
    -0.49
     sufficiently
    -0.49
     drastically
    -0.49
     naturally
    -0.49
    POSITIVE LOGITS
    ullivan
    0.63
    çĶ°
    0.61
    itto
    0.56
     TBA
    0.55
    ĪĴ
    0.55
    negie
    0.53
     respectively
    0.53
    ikuman
    0.52
    imental
    0.51
     etc
    0.50
    Act Density 1.166%

    No Known Activations