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

    Neuronpedia

    INDEX
    Explanations

    activities and processes related to writing and filmmaking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after indefinite articles ("a," "an")

    np_acts-logits-general · gemini-2.0-flash

    steps are addressed incrementally

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.63
     cesse
    -0.58
     nữa
    -0.54
    paravant
    -0.53
    onsored
    -0.52
    Референце
    -0.51
     ujednoznacz
    -0.51
    jména
    -0.51
    Bronnen
    -0.50
     constantes
    -0.50
    POSITIVE LOGITS
     head
    1.27
     step
    1.19
     word
    1.02
     inch
    0.87
    step
    0.87
     point
    0.83
     layer
    0.80
     toe
    0.79
    head
    0.79
     tooth
    0.79
    Act Density 0.508%

    No Known Activations