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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing superlatives and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    824
    -0.17
     Tul
    -0.17
    æĽ²
    -0.16
    ML
    -0.15
    863
    -0.15
    kara
    -0.15
    究
    -0.15
     no
    -0.15
     Klo
    -0.14
    ingers
    -0.14
    POSITIVE LOGITS
    hev
    0.16
    رÙĪع
    0.15
     ever
    0.15
     nunca
    0.15
    never
    0.14
    ever
    0.14
     ilg
    0.14
     reife
    0.14
     unprecedented
    0.14
    -ever
    0.14
    Act Density 0.083%

    No Known Activations