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

    Neuronpedia

    INDEX
    Explanations

    serious or escalating problems and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    figcaption
    -0.15
    -cols
    -0.15
    zend
    -0.15
    enburg
    -0.14
    anut
    -0.14
    леÑĩ
    -0.14
    ulis
    -0.14
    ÙıÙĪÙĨ
    -0.14
    assis
    -0.14
    askell
    -0.13
    POSITIVE LOGITS
     when
    0.20
    aje
    0.16
    when
    0.15
     directions
    0.15
    278
    0.15
     cuando
    0.15
    egra
    0.14
     lorsque
    0.14
    afa
    0.14
    ίκ
    0.14
    Act Density 0.173%

    No Known Activations