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

    Neuronpedia

    INDEX
    Explanations

    terms related to honor and recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     honoured
    -0.19
     honour
    -0.17
    íĻľ
    -0.16
    esi
    -0.16
    erne
    -0.16
    quarters
    -0.15
     honoring
    -0.15
     honors
    -0.15
    endor
    -0.15
    esse
    -0.14
    POSITIVE LOGITS
    ific
    0.38
    ably
    0.35
    able
    0.30
    arium
    0.28
    ABLE
    0.25
    IFIC
    0.24
    ables
    0.23
    atus
    0.21
    bound
    0.20
     roll
    0.20
    Act Density 0.021%

    No Known Activations