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

    Neuronpedia

    INDEX
    Explanations

    terms related to URLs, web technology, and online references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dit
    -0.15
    baz
    -0.14
    itar
    -0.14
    ÙĦاÙĨ
    -0.14
    830
    -0.14
    owan
    -0.14
     å¯
    -0.14
    çĽ
    -0.13
    NullOr
    -0.13
    umer
    -0.13
    POSITIVE LOGITS
    IRA
    0.17
    oca
    0.16
    ysa
    0.15
    eli
    0.15
    aza
    0.14
    oji
    0.14
     Whe
    0.14
    .defaults
    0.14
    brace
    0.14
    Ing
    0.14
    Act Density 0.008%

    No Known Activations