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

    Neuronpedia

    INDEX
    Explanations

    words related to transitions or changes in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĵn
    -0.15
    rack
    -0.15
    oment
    -0.14
    owing
    -0.14
    untu
    -0.14
    سÙĩ
    -0.13
    ÏĨαÏģ
    -0.13
    ady
    -0.13
    stadt
    -0.13
    неÑģÑĤи
    -0.13
    POSITIVE LOGITS
    gon
    0.19
    pad
    0.17
     transitions
    0.15
    anan
    0.15
    obra
    0.14
    transition
    0.14
    Ñħод
    0.14
    ives
    0.14
    .transition
    0.14
    uan
    0.14
    Act Density 0.007%

    No Known Activations