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

    Neuronpedia

    INDEX
    Explanations

    expressions of strong dislike or hatred towards various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elles
    -0.20
    ales
    -0.16
    utsch
    -0.16
    lass
    -0.15
    illo
    -0.15
     DependencyProperty
    -0.14
    496
    -0.14
     боÑı
    -0.14
     ÅĤ
    -0.14
     пÑĢиÑĤ
    -0.14
    POSITIVE LOGITS
    è¾°
    0.17
    enez
    0.16
    luck
    0.14
    ovny
    0.14
    anst
    0.14
     undermin
    0.14
    sst
    0.14
    amet
    0.14
    aea
    0.14
    ิà¹ī
    0.14
    Act Density 0.072%

    No Known Activations