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

    Neuronpedia

    INDEX
    Explanations

    sentences suggesting signing up for newsletters or similar subscriptions

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing personal recommendations or content suggestions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -0.58
     millisec
    -0.57
     polyg
    -0.56
     destro
    -0.54
     narrator
    -0.54
     designation
    -0.54
     sovere
    -0.54
    thora
    -0.54
     pioneer
    -0.53
    =~
    -0.52
    POSITIVE LOGITS
    Increases
    0.71
    gdala
    0.70
    herty
    0.65
     Subscribe
    0.65
    bleacher
    0.64
    hazard
    0.64
    etry
    0.63
    lift
    0.62
    icious
    0.61
    inson
    0.61
    Act Density 0.050%

    No Known Activations