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

    Neuronpedia

    INDEX
    Explanations

    terms related to data collection and privacy policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ashi
    -0.18
    elage
    -0.16
    ierz
    -0.14
     Mits
    -0.14
    olk
    -0.14
    ark
    -0.13
     Hus
    -0.13
    áš
    -0.13
    _sensitive
    -0.13
    iedades
    -0.13
    POSITIVE LOGITS
    Anonymous
    0.26
     Anonymous
    0.26
    åĮ
    0.24
     anonymous
    0.24
    anonymous
    0.21
    anon
    0.21
     anonymously
    0.21
     anonym
    0.21
     anon
    0.20
    ga
    0.17
    Act Density 0.011%

    No Known Activations