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

    Neuronpedia

    INDEX
    Explanations

    references to people and their interactions in a narrative context

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

    Follows a person/pronoun who is speaking

    np_acts-logits-general · gemini-2.0-flash

    reporting speech and dialogue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    interopRequire
    -0.77
    OrNil
    -0.55
    StoryboardSegue
    -0.53
    Cubit
    -0.51
    SBATCH
    -0.48
    Ranks
    -0.47
    Threading
    -0.47
     genero
    -0.44
    ACTED
    -0.44
    lnie
    -0.43
    POSITIVE LOGITS
     saying
    2.08
     said
    2.07
     say
    1.96
     says
    1.89
    Said
    1.75
    said
    1.72
    saying
    1.70
     Said
    1.66
     Says
    1.62
     berkata
    1.61
    Act Density 0.305%

    No Known Activations