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

    Neuronpedia

    INDEX
    Explanations

    phrases involving conjunctions connecting different elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nier
    -0.15
    cname
    -0.15
    itud
    -0.15
    idis
    -0.15
    utos
    -0.14
    zz
    -0.14
    év
    -0.14
    olygon
    -0.14
     swe
    -0.14
    kke
    -0.14
    POSITIVE LOGITS
    amp
    0.28
    AMP
    0.23
    erson
    0.23
    /or
    0.23
     amp
    0.22
    reas
    0.18
    amento
    0.18
     anon
    0.17
    rade
    0.17
    vanced
    0.17
    Act Density 0.152%

    No Known Activations