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

    Neuronpedia

    INDEX
    Explanations

    words indicating exclusivity or limitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Bermuda
    -0.64
     Sahara
    -0.62
    McGraw
    -0.61
     Zanzibar
    -0.59
     HDF
    -0.58
     Minangkabau
    -0.56
    المراجع
    -0.55
     Poincaré
    -0.55
     Bermuda
    -0.54
     bermuda
    -0.54
    POSITIVE LOGITS
    +:+
    0.86
    DockStyle
    0.77
    aarrggbb
    0.74
    nsic
    0.71
    ocities
    0.70
     المعيارى
    0.69
    üyada
    0.69
     the
    0.69
     Paglinawan
    0.67
    deepcopy
    0.67
    Act Density 0.324%

    No Known Activations