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

    Neuronpedia

    INDEX
    Explanations

    pronouns and possessive determiners referring to people

    oai_token-act-pair · gpt-3.5-turbo

    affirmations of individual capability and group dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Canaver
    -0.61
     charism
    -0.61
     recognition
    -0.59
     monopoly
    -0.59
    assetsadobe
    -0.58
     Dayton
    -0.58
     renewables
    -0.58
     composite
    -0.57
     PowerPoint
    -0.56
     loudspe
    -0.56
    POSITIVE LOGITS
    ÃĥÃĤ
    1.27
    ÃĥÃĤÃĥÃĤ
    1.20
    îĢ
    1.19
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    1.15
    ^^
    1.14
    âĶ
    1.11
    ^
    1.10
    «
    1.08
    |
    1.03
    `
    1.02
    Act Density 0.995%

    No Known Activations