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

    Neuronpedia

    INDEX
    Explanations

    mentions of defensive actions or strategies

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to confrontation or combat scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urches
    -0.77
     encount
    -0.67
    IVERS
    -0.67
     pioneers
    -0.65
     selves
    -0.65
     millenn
    -0.65
     proponents
    -0.61
     saints
    -0.61
     promoters
    -0.61
    arij
    -0.60
    POSITIVE LOGITS
     theirs
    0.96
     himself
    0.90
     hers
    0.88
     herself
    0.71
     whom
    0.68
     Himself
    0.65
    heit
    0.65
     his
    0.64
     him
    0.62
    stretched
    0.60
    Act Density 0.885%

    No Known Activations