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

    Neuronpedia

    INDEX
    Explanations

    elements related to simplicity and complexity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undi
    -0.19
    ldre
    -0.15
    lossen
    -0.14
     Vaughan
    -0.14
    ci
    -0.14
     ci
    -0.14
    aldi
    -0.14
    èªĮ
    -0.14
    ood
    -0.14
    vere
    -0.14
    POSITIVE LOGITS
     Cock
    0.18
    ius
    0.17
     cock
    0.15
    viz
    0.15
     dj
    0.14
     Assigned
    0.14
    cock
    0.14
    _NT
    0.14
     kre
    0.14
     Fu
    0.14
    Act Density 0.029%

    No Known Activations