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

    Neuronpedia

    INDEX
    Explanations

    phrases related to investigations and allegations of misconduct

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fet
    -0.15
    avia
    -0.14
    atri
    -0.14
    mlin
    -0.14
     attacker
    -0.14
     insult
    -0.14
    ayment
    -0.13
     truyá»ģn
    -0.13
     burg
    -0.13
     Hang
    -0.13
    POSITIVE LOGITS
     abuse
    0.25
     mal
    0.24
     im
    0.23
     abuses
    0.23
     systemic
    0.23
     wrongdoing
    0.23
     widespread
    0.23
     wides
    0.23
     instances
    0.23
     serious
    0.22
    Act Density 0.286%

    No Known Activations