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

    Neuronpedia

    INDEX
    Explanations

    instances of future plans or intentions expressed in a text

    oai_token-act-pair · gpt-3.5-turbo

    the word "on" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ï¸ı
    -0.87
    SPA
    -0.74
    soDeliveryDate
    -0.73
     Fram
    -0.73
    sworth
    -0.71
    BuyableInstoreAndOnline
    -0.68
    QUI
    -0.66
    wine
    -0.66
    Bridge
    -0.64
    FBI
    -0.64
    POSITIVE LOGITS
     behalf
    1.09
    eday
    0.88
    etheless
    0.87
    erous
    0.82
     arrival
    0.81
     occas
    0.78
     relinqu
    0.77
     preserving
    0.76
    clusions
    0.74
     merit
    0.73
    Act Density 0.097%

    No Known Activations