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

    Neuronpedia

    INDEX
    Explanations

    repeated mentions of being accused of wrongdoing or criminal activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ViewImports
    -0.68
     pinulongan
    -0.62
    ToBounds
    -0.59
    StructEnd
    -0.59
    MergeFrom
    -0.57
    phrine
    -0.57
    rijk
    -0.56
    qtype
    -0.56
    onAttach
    -0.53
    APORE
    -0.52
    POSITIVE LOGITS
     accused
    1.89
    accu
    1.34
     accuse
    1.20
     accuses
    1.07
     accus
    1.00
     accusing
    0.98
     acus
    0.90
     acusado
    0.89
     accusations
    0.89
     accusation
    0.79
    Act Density 0.059%

    No Known Activations