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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "If you," often used in informative or instructional contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate user engagement or interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "},
    -0.76
    ".[
    -0.71
    acements
    -0.66
    Exactly
    -0.63
    .[
    -0.61
    feat
    -0.60
    Els
    -0.60
    Bridge
    -0.60
     Promise
    -0.59
    Improved
    -0.58
    POSITIVE LOGITS
     yourself
    0.92
     yourselves
    0.84
    odcast
    0.76
    audi
    0.70
     wondering
    0.67
     podcasts
    0.67
     anniversary
    0.67
     lucky
    0.67
    watching
    0.66
     subscribed
    0.66
    Act Density 0.433%

    No Known Activations