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

    Neuronpedia

    INDEX
    Explanations

    specific phrases and structures related to qualitative assessments and comparisons in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sul
    -0.18
    Suffix
    -0.16
    Suc
    -0.16
    ani
    -0.15
     Steele
    -0.15
    :maj
    -0.14
    تÙĩا
    -0.14
     Schro
    -0.14
    TestCategory
    -0.14
     Symphony
    -0.14
    POSITIVE LOGITS
     sense
    0.84
    sense
    0.67
     Sense
    0.64
    Sense
    0.57
     sentido
    0.51
     senses
    0.49
    SEN
    0.47
     scn
    0.44
    ense
    0.42
     sens
    0.41
    Act Density 0.061%

    No Known Activations