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

    Neuronpedia

    INDEX
    Explanations

    statements or quotations in a text

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and their contexts in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sqor
    -0.71
     playbook
    -0.61
     bureaucracy
    -0.54
    uristic
    -0.54
    yt
    -0.53
     peek
    -0.51
     liv
    -0.51
     negotiating
    -0.51
     odor
    -0.51
     favor
    -0.50
    POSITIVE LOGITS
    Meanwhile
    0.89
    Elsewhere
    0.82
    Later
    0.76
    Quotes
    0.75
    Asked
    0.73
    However
    0.73
    Other
    0.72
    Trivia
    0.72
    Similarly
    0.71
    Others
    0.69
    Act Density 0.570%

    No Known Activations