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

    Neuronpedia

    INDEX
    Explanations

    terms related to data transmission

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     indisponible
    -0.60
     safely
    -0.60
     villager
    -0.58
     Gaulle
    -0.57
    cipar
    -0.56
     мәкал
    -0.54
     McNamara
    -0.54
     Winslow
    -0.51
    vini
    -0.51
    ADELPHIA
    -0.51
    POSITIVE LOGITS
     severely
    1.19
     profoundly
    1.07
     gravely
    0.96
     disturbed
    0.94
     greatly
    0.92
     deeply
    0.92
     critically
    0.91
     thoroughly
    0.88
    heav
    0.87
     hugely
    0.84
    Act Density 0.093%

    No Known Activations