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

    Neuronpedia

    INDEX
    Explanations

    references to comments or writings from individuals and reviewers

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

    authors and reviewers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.54
     conferencias
    -0.42
     entrevistas
    -0.39
    onAttach
    -0.38
     reuniones
    -0.36
    abestanden
    -0.35
    BASEPATH
    -0.35
     pequenas
    -0.35
     wewnętr
    -0.35
    Scénario
    -0.34
    POSITIVE LOGITS
     commenter
    0.88
     someone
    0.79
     others
    0.79
    Others
    0.73
     Others
    0.72
    someone
    0.70
    Someone
    0.69
     somebody
    0.69
     Someone
    0.69
    httphttps
    0.67
    Act Density 0.008%

    No Known Activations