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

    Neuronpedia

    INDEX
    Explanations

    phrases related to something being full of a specific quality or attribute

    oai_token-act-pair · gpt-3.5-turbo

    phrases centered around the concept of being "full of" something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     confir
    -0.73
    Ń·
    -0.71
    ramid
    -0.69
    UA
    -0.69
    raviolet
    -0.67
    antha
    -0.67
     proport
    -0.65
    gradation
    -0.65
    ARS
    -0.64
     mathemat
    -0.64
    POSITIVE LOGITS
     surprises
    1.07
     sorts
    0.78
     interesting
    0.77
     juicy
    0.77
     holes
    0.76
     fresh
    0.75
     seasoned
    0.74
     calories
    0.72
     crap
    0.71
     goodies
    0.71
    Act Density 0.042%

    No Known Activations