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

    Neuronpedia

    INDEX
    Explanations

    words related to visibility or the act of being seen

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     devenus
    -0.68
    ="#"><
    -0.63
    Revis
    -0.62
     morire
    -0.59
     henvisninger
    -0.58
    ('/
    -0.58
    унк
    -0.58
     sacré
    -0.58
    Tania
    -0.58
    JSONException
    -0.57
    POSITIVE LOGITS
     Visibility
    0.97
     Visible
    0.93
    visible
    0.87
     Kyr
    0.85
     myſelf
    0.85
     visible
    0.84
    Visibility
    0.84
     themſelves
    0.84
     poffible
    0.83
     Christo
    0.82
    Act Density 0.007%

    No Known Activations