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

    Neuronpedia

    INDEX
    Explanations

    phrases related to issues of legitimacy and security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ichtig
    -0.17
    @Spring
    -0.15
    anga
    -0.14
     LENG
    -0.14
    AWN
    -0.14
    ikel
    -0.14
    aight
    -0.14
    iná
    -0.14
     abst
    -0.14
     ÐĴики
    -0.14
    POSITIVE LOGITS
     endangered
    0.27
     challenged
    0.26
     threatened
    0.26
     compromised
    0.23
     questioned
    0.23
     violated
    0.22
     shaken
    0.21
     dashed
    0.21
    -threat
    0.21
     thrown
    0.21
    Act Density 0.186%

    No Known Activations