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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks indicating pauses or breaks in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hoe
    -0.76
    robe
    -0.70
    eln
    -0.64
     Secrets
    -0.64
    obia
    -0.63
    RPG
    -0.59
     GEAR
    -0.59
    itaire
    -0.59
    ESSION
    -0.59
     Medals
    -0.59
    POSITIVE LOGITS
     albeit
    1.17
     uh
    0.98
     um
    0.95
     unnamed
    0.81
    albeit
    0.76
     overlapping
    0.72
     fateful
    0.70
     though
    0.70
     subt
    0.69
     unidentified
    0.68
    Act Density 0.112%

    No Known Activations