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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to research findings and conclusions in scientific studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     every
    -0.51
    every
    -0.47
     Anyone
    -0.46
     Вот
    -0.45
     anytime
    -0.45
     each
    -0.44
     &___
    -0.44
     Anybody
    -0.42
     Every
    -0.42
     anyone
    -0.41
    POSITIVE LOGITS
     Interestingly
    0.97
    Interestingly
    0.95
     interestingly
    0.87
     Surprisingly
    0.80
    Consistent
    0.79
    Surprisingly
    0.79
     strikingly
    0.77
     Consistent
    0.77
     surprisingly
    0.74
     intrigu
    0.72
    Act Density 1.886%

    No Known Activations