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

    Neuronpedia

    INDEX
    Explanations

    words related to negative emotions, particularly hatred and disgust

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    negative emotions and contempt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ivy
    -0.65
    Ivy
    -0.64
     yore
    -0.61
     inadvert
    -0.60
    Epi
    -0.59
     Epi
    -0.57
     blurb
    -0.57
    Stride
    -0.55
    serif
    -0.54
     popsic
    -0.54
    POSITIVE LOGITS
     hatred
    0.77
    ormais
    0.55
     inoxidable
    0.49
     odeur
    0.45
     hated
    0.45
     inoxid
    0.45
     älskar
    0.44
    shocked
    0.44
     élastique
    0.43
    hetto
    0.43
    Act Density 0.007%

    No Known Activations