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

    Neuronpedia

    INDEX
    Explanations

    phrases related to financial transactions or documents

    oai_token-act-pair · gpt-3.5-turbo

    frequent occurrences of the word "the" and other common words associated with specific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.84
    .''
    -0.80
    anooga
    -0.80
    .</
    -0.76
     nonetheless
    -0.75
    ingly
    -0.73
    cum
    -0.72
    .<
    -0.72
    /
    -0.69
    ,...
    -0.67
    POSITIVE LOGITS
     aforementioned
    1.26
     foregoing
    1.06
     original
    0.98
     above
    0.93
     remainder
    0.91
     entire
    0.89
     initial
    0.88
     rest
    0.88
     afore
    0.87
     remaining
    0.84
    Act Density 0.711%

    No Known Activations