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

    Neuronpedia

    INDEX
    Explanations

    expressions of fundamental qualities or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     continúas
    -0.50
     يتيمه
    -0.49
    afficheront
    -0.44
     didst
    -0.43
     Superhost
    -0.43
    spreis
    -0.43
     canst
    -0.43
    -0.43
    (%)
    -0.42
    expandindo
    -0.42
    POSITIVE LOGITS
     fundamentally
    1.03
     genuinely
    0.91
     absolutely
    0.84
     essentially
    0.82
     utterly
    0.82
     truly
    0.80
     entirely
    0.79
     Essentially
    0.78
    absolutely
    0.78
    Essentially
    0.77
    Act Density 1.956%

    No Known Activations