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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "two" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    renheit
    -0.87
    Ô
    -0.82
    ugu
    -0.80
    schild
    -0.79
    za
    -0.77
    agher
    -0.74
    ategory
    -0.74
    ovi
    -0.73
    gallery
    -0.72
    nect
    -0.72
    POSITIVE LOGITS
     halves
    1.51
     sides
    1.26
     thirds
    1.18
     sexes
    1.11
    fold
    1.04
     Kore
    1.01
     parties
    0.95
     extremes
    0.95
     dozen
    0.88
     brothers
    0.85
    Act Density 0.041%

    No Known Activations