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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical specifications or descriptions of machinery or vehicles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ation
    -0.56
      
    -0.54
     Tri
    -0.53
     tarko
    -0.53
    Namara
    -0.52
    citas
    -0.51
    explique
    -0.49
    ↵↵
    -0.49
    ेशन
    -0.49
    iertas
    -0.49
    POSITIVE LOGITS
     TO
    1.10
     to
    1.07
    to
    0.95
    To
    0.94
    ToAction
    0.87
    yto
    0.87
     To
    0.85
    TO
    0.85
     να
    0.84
     Toh
    0.84
    Act Density 0.236%

    No Known Activations