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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or specific entities among various examples

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to groups or collections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irez
    -0.70
    adian
    -0.70
    ifix
    -0.66
    nery
    -0.64
    idia
    -0.64
    bane
    -0.63
    agos
    -0.62
    oldemort
    -0.57
    ysc
    -0.57
    iltr
    -0.56
    POSITIVE LOGITS
    st
    0.84
    IJ
    0.83
    among
    0.69
     others
    0.69
    ī
    0.69
    ĪĴ
    0.69
    Īè
    0.68
    stad
    0.67
    ¸
    0.66
     whom
    0.64
    Act Density 0.027%

    No Known Activations