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

    Neuronpedia

    INDEX
    Explanations

    references to a specific person's actions and discussions surrounding high-profile events or political situations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Queste
    -0.62
     Altri
    -0.61
     Infatti
    -0.59
    Beskrivning
    -0.59
     Mentre
    -0.56
     vedno
    -0.56
     Inoltre
    -0.55
     pravi
    -0.55
     Ciò
    -0.55
    tidaknya
    -0.54
    POSITIVE LOGITS
     COME
    1.18
    come
    1.16
    Come
    1.15
     Come
    1.14
     come
    1.12
    COME
    0.99
     COMES
    0.95
     Kome
    0.87
    comes
    0.86
     comes
    0.84
    Act Density 0.117%

    No Known Activations