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

    Neuronpedia

    INDEX
    Explanations

    references to bonds or relationships between individuals or groups

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     pessi
    -0.97
     zyn
    -0.97
     solidar
    -0.96
     kram
    -0.90
    amaño
    -0.89
     utop
    -0.89
     patrio
    -0.88
     bera
    -0.87
     hina
    -0.85
     obligator
    -0.85
    POSITIVE LOGITS
     of
    0.77
     eût
    0.70
     quoique
    0.70
    Kenmerken
    0.64
     disait
    0.61
     croit
    0.61
     reconnaît
    0.60
     venait
    0.59
     paraît
    0.59
     semblait
    0.59
    Act Density 0.522%

    No Known Activations