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

    Neuronpedia

    INDEX
    Explanations

    references to the current state or situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    QMetaType
    -1.00
     jurado
    -0.86
     Sph
    -0.84
    lehem
    -0.81
     McCoy
    -0.80
     sauvages
    -0.77
     voudrais
    -0.77
     Tolstoy
    -0.77
     vendus
    -0.74
    Koh
    -0.74
    POSITIVE LOGITS
     current
    2.44
     Current
    2.26
    current
    2.20
    CURRENT
    2.19
     CURRENT
    2.14
    Current
    2.08
     curent
    1.75
     currents
    1.57
     Currents
    1.54
    urrent
    1.48
    Act Density 0.106%

    No Known Activations