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

    Neuronpedia

    INDEX
    Explanations

    quotations within text

    oai_token-act-pair · gpt-3.5-turbo

    quoted speech or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     favor
    -0.79
     rumored
    -0.77
     honors
    -0.75
     livestream
    -0.74
     catalog
    -0.72
     grades
    -0.69
     signaling
    -0.69
     enroll
    -0.68
     Lamar
    -0.67
     midterm
    -0.66
    POSITIVE LOGITS
    We
    1.07
    Firstly
    1.06
    Interest
    1.01
    There
    0.97
    BBC
    0.96
    It
    0.96
    Our
    0.94
    Obviously
    0.94
    Certainly
    0.94
    Therefore
    0.94
    Act Density 0.119%

    No Known Activations