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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "writing."

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

    agreed to in writing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arangay
    -0.54
    pecabe
    -0.52
    enumii
    -0.52
     indígen
    -0.51
    -0.49
     ujednoznacz
    -0.49
    ésult
    -0.48
    IBLIO
    -0.48
     Agung
    -0.47
     avoient
    -0.47
    POSITIVE LOGITS
     writing
    0.95
     Writing
    0.79
    writing
    0.77
    Writing
    0.74
     WRITING
    0.69
    WRITING
    0.61
     écrit
    0.58
     writings
    0.55
     écrire
    0.54
     wrote
    0.52
    Act Density 0.005%

    No Known Activations