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

    Neuronpedia

    INDEX
    Explanations

    phrases related to criminal behavior or legal issues

    oai_token-act-pair · gpt-3.5-turbo

    terms related to delinquency and education

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avorite
    -0.71
    Reviewer
    -0.69
     clad
    -0.67
     defending
    -0.66
    ographical
    -0.64
    astern
    -0.63
    ographically
    -0.62
     crabs
    -0.62
     Alban
    -0.61
     illusions
    -0.61
    POSITIVE LOGITS
    ual
    1.33
    uates
    1.32
    uation
    1.32
    ually
    1.27
    io
    1.21
    uating
    1.17
    uated
    1.16
    ional
    1.15
    ency
    1.15
    iosity
    1.14
    Act Density 0.080%

    No Known Activations