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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating meeting or failing to meet expectations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that relate to meeting or failing to meet expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etsk
    -0.88
     unavailable
    -0.74
     delay
    -0.60
     Ruin
    -0.60
    lessness
    -0.60
     fuss
    -0.59
    things
    -0.59
     Subtle
    -0.59
    thing
    -0.56
     inaction
    -0.55
    POSITIVE LOGITS
     to
    0.71
    To
    0.71
    heit
    0.69
     TO
    0.68
    Registered
    0.67
     thereto
    0.67
    ulia
    0.66
    SOURCE
    0.65
    BuyableInstoreAndOnline
    0.64
    iola
    0.61
    Act Density 0.262%

    No Known Activations