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

    Neuronpedia

    INDEX
    Explanations

    references to the presence of non-conformity and its consequences within a community

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    expandindo
    -0.62
    Viited
    -0.55
     amitié
    -0.52
     pourtant
    -0.51
    حوالہ
    -0.51
     största
    -0.49
     peindre
    -0.49
     extrême
    -0.49
     skjer
    -0.48
    Przypisy
    -0.48
    POSITIVE LOGITS
    ukone
    0.61
    NavigationView
    0.57
    ,))
    0.57
    hnia
    0.56
    OpenHelper
    0.56
     mortals
    0.53
    phosa
    0.53
     dwell
    0.52
     intruders
    0.52
    ReactDOM
    0.51
    Act Density 0.228%

    No Known Activations