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

    Neuronpedia

    INDEX
    Explanations

    fragments of casual conversation containing phrases like "I think," "And I think," and "you hear that."

    oai_token-act-pair · gpt-3.5-turbo

    instances of personal opinions or beliefs expressed in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¼ãĤ¦ãĤ¹
    -0.82
    ¨
    -0.78
    ãĥ¯ãĥ³
    -0.77
    COMPLE
    -0.77
    eaturing
    -0.76
    ¶ħ
    -0.71
     comprised
    -0.71
    cele
    -0.71
    Þ
    -0.71
     victorious
    -0.70
    POSITIVE LOGITS
     maybe
    0.90
    Alternatively
    0.89
    maybe
    0.87
     anecdotal
    0.83
     argues
    0.82
    Maybe
    0.82
     Suppose
    0.82
     Maybe
    0.81
     bothers
    0.79
    Others
    0.79
    Act Density 0.793%

    No Known Activations