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

    Neuronpedia

    INDEX
    Explanations

    references to large sizes or weights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     small
    -0.66
     tiny
    -0.64
    Small
    -0.63
     Small
    -0.57
     piccolo
    -0.57
     μικ
    -0.56
     kecil
    -0.56
    เล็ก
    -0.55
    small
    -0.54
     petits
    -0.53
    POSITIVE LOGITS
     giant
    1.30
     behe
    1.28
     gigantic
    1.19
    giant
    1.16
     massive
    1.13
     heavyweight
    1.13
    Massive
    1.10
     mammoth
    1.08
     Giant
    1.07
     colossal
    1.07
    Act Density 0.286%

    No Known Activations