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

    Neuronpedia

    INDEX
    Explanations

    phrases related to subscriptions and support for journalism

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and the presence of expressions of gratitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rehearsal
    -0.61
    ogical
    -0.59
    isphere
    -0.59
    geist
    -0.57
    iquid
    -0.55
     examiner
    -0.54
    umbai
    -0.54
    ewitness
    -0.54
     theor
    -0.54
    llah
    -0.53
    POSITIVE LOGITS
     Thank
    0.69
     Thanks
    0.67
     Enhance
    0.62
     Become
    0.62
     THANK
    0.62
     Purch
    0.59
     Restrict
    0.58
     SIGN
    0.58
     Powered
    0.57
     Veh
    0.57
    Act Density 0.021%

    No Known Activations