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

    Neuronpedia

    INDEX
    Explanations

    words related to illegal actions or controversy

    oai_token-act-pair · gpt-3.5-turbo

    forms of verbs related to social actions, particularly in political or legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rious
    -0.75
    ndra
    -0.75
    ufact
    -0.74
    icter
    -0.72
    ringe
    -0.71
     ancest
    -0.70
    vier
    -0.69
    herty
    -0.68
    onal
    -0.67
    bably
    -0.67
    POSITIVE LOGITS
    à
    0.72
     spree
    0.71
     havoc
    0.67
    mong
    0.66
    à¨
    0.65
     Anonymous
    0.64
     Mum
    0.64
    ilee
    0.64
    adelphia
    0.62
    ebin
    0.62
    Act Density 0.182%

    No Known Activations