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

    Neuronpedia

    INDEX
    Explanations

    interactions and relationships among family members

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fsp
    -0.17
    erule
    -0.16
    arel
    -0.15
    etik
    -0.15
    &o
    -0.14
    allen
    -0.14
    illis
    -0.14
    rious
    -0.13
    riere
    -0.13
    inar
    -0.13
    POSITIVE LOGITS
     convince
    0.52
     persu
    0.50
     convincing
    0.49
     persuade
    0.49
     convin
    0.47
     persuasion
    0.46
     persuaded
    0.44
     convinced
    0.43
     persuasive
    0.43
     pressure
    0.42
    Act Density 0.595%

    No Known Activations