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

    Neuronpedia

    INDEX
    Explanations

    instances of extreme or intense situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raj
    -0.17
    allis
    -0.16
    784
    -0.15
    ere
    -0.15
    2
    -0.15
     Dere
    -0.15
    align
    -0.14
    erez
    -0.14
    aligned
    -0.14
    èģĶ
    -0.14
    POSITIVE LOGITS
    Warm
    0.25
     Warm
    0.25
     warm
    0.25
    warm
    0.23
     warmth
    0.20
     warmer
    0.20
     warming
    0.18
     warmed
    0.16
    ãĤ¿ãĥ³
    0.15
     ÑĤеп
    0.15
    Act Density 0.026%

    No Known Activations