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

    Neuronpedia

    INDEX
    Explanations

    phrases that express emphasis on particular practices or themes within professional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    auc
    -0.15
    laus
    -0.14
    handlers
    -0.14
    âu
    -0.14
    ivol
    -0.13
    ilim
    -0.13
    aura
    -0.13
    incer
    -0.13
    tega
    -0.13
    기ìĹIJ
    -0.13
    POSITIVE LOGITS
     emphasis
    0.57
    emphasis
    0.45
     focus
    0.42
     particular
    0.41
     accent
    0.38
     emphasize
    0.38
    phasis
    0.36
     Em
    0.35
     special
    0.35
     especial
    0.35
    Act Density 0.087%

    No Known Activations