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

    Neuronpedia

    INDEX
    Explanations

    verbs related to political actions and statements

    oai_token-act-pair · gpt-3.5-turbo

    statements of personal responsibility or political accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izens
    -0.68
    ORY
    -0.67
    ãħĭãħĭ
    -0.66
     pricey
    -0.64
    Mix
    -0.61
     })
    -0.59
     endif
    -0.59
    })
    -0.58
    pload
    -0.58
     mutants
    -0.58
    POSITIVE LOGITS
     myself
    1.59
     my
    1.17
     personally
    1.06
     respectfully
    0.89
    Statement
    0.83
    displayText
    0.82
     solemn
    0.82
     âĢ¦"
    0.78
     hereby
    0.78
     sworn
    0.76
    Act Density 0.678%

    No Known Activations