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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and variations of the word "unbounded"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "unb" and references to rebellion or conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Viet
    -0.76
    aval
    -0.75
     Nose
    -0.72
    sis
    -0.72
     Seymour
    -0.71
     Mast
    -0.68
     Scher
    -0.67
    vas
    -0.65
    oot
    -0.65
    zza
    -0.63
    POSITIVE LOGITS
     unb
    3.53
     Reb
    1.17
     forb
    1.14
    reb
    1.04
    anan
    0.87
     Barth
    0.87
    erb
    0.85
     inval
    0.84
     infinite
    0.83
     overd
    0.81
    Act Density 0.039%

    No Known Activations