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

    Neuronpedia

    INDEX
    Explanations

    concepts related to societal and personal standards of morality and integrity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iná
    -0.16
    aight
    -0.16
    oley
    -0.16
    ìĬµ
    -0.15
    ikip
    -0.15
    KNOWN
    -0.14
     ÐĴики
    -0.14
    @Spring
    -0.14
    галÑĸ
    -0.14
    ichtig
    -0.14
    POSITIVE LOGITS
     er
    0.30
     challenged
    0.29
     threatened
    0.28
     endangered
    0.28
     questioned
    0.27
    -threat
    0.25
     compromised
    0.24
     tested
    0.23
     shaken
    0.23
     dashed
    0.21
    Act Density 0.208%

    No Known Activations