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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing the quality of experiences or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utting
    -0.16
    ÙĬØ«
    -0.15
    òa
    -0.14
    ohan
    -0.14
    oksen
    -0.14
    ofs
    -0.13
     [[]
    -0.13
    anded
    -0.13
    cono
    -0.13
    isté
    -0.13
    POSITIVE LOGITS
     few
    0.39
     couple
    0.35
     start
    0.30
    few
    0.29
    Few
    0.27
     Few
    0.26
     time
    0.26
     experience
    0.24
     stretch
    0.23
     ride
    0.23
    Act Density 0.055%

    No Known Activations