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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or specific names that are likely to be entities or organizations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "called" in relation to names or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inth
    -0.70
    jee
    -0.69
     isolate
    -0.64
    SPONSORED
    -0.64
    ento
    -0.63
    ±
    -0.63
     practiced
    -0.62
    cise
    -0.62
    -------------
    -0.62
     drained
    -0.61
    POSITIVE LOGITS
     Operation
    0.92
     "#
    0.87
     Lif
    0.82
     Attention
    0.82
     Amb
    0.80
     Samar
    0.80
     "
    0.77
     Trace
    0.76
     Rise
    0.76
     "@
    0.76
    Act Density 0.054%

    No Known Activations