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

    Neuronpedia

    INDEX
    Explanations

    phrases associated with societal issues and community feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wanting
    -0.14
    okit
    -0.14
    ãģĤãĤĬ
    -0.14
    lant
    -0.14
    ét
    -0.14
    å¾Īå¤ļ
    -0.14
    .FindElement
    -0.13
    Ľå»º
    -0.13
    -using
    -0.13
    changed
    -0.13
    POSITIVE LOGITS
    asal
    0.16
    arth
    0.15
    SCII
    0.14
    ICAST
    0.13
    acic
    0.13
    icha
    0.13
    argin
    0.13
     NotSupportedException
    0.13
    ICollection
    0.13
     unfortunate
    0.13
    Act Density 0.080%

    No Known Activations