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

    Neuronpedia

    INDEX
    Explanations

    references to academic proceedings and conferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.42
    󠁿
    -0.41
    enegro
    -0.40
    どうか
    -0.38
    inthians
    -0.36
    marginRight
    -0.36
     marginLeft
    -0.36
    UTM
    -0.35
     Health
    -0.35
    yskland
    -0.35
    POSITIVE LOGITS
     Proceedings
    0.79
    Proceedings
    0.70
     Proc
    0.63
     proceedings
    0.62
    Proc
    0.57
    ceedings
    0.57
     PROCEEDINGS
    0.56
    ьаж
    0.52
     acta
    0.50
     Proceeding
    0.47
    Act Density 0.277%

    No Known Activations