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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating measurements or distances in competitive contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ç¬
    -0.17
    ember
    -0.16
    annis
    -0.16
    .tp
    -0.14
    leigh
    -0.14
    -metal
    -0.14
    ISCO
    -0.14
    á»ĵn
    -0.14
    å´
    -0.14
     vez
    -0.13
    POSITIVE LOGITS
    339
    0.17
    679
    0.15
     ws
    0.15
    esser
    0.15
    olia
    0.15
     åŁ
    0.14
     Cheng
    0.14
    è£ģ
    0.14
    358
    0.14
     Hyde
    0.14
    Act Density 0.015%

    No Known Activations