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

    Neuronpedia

    INDEX
    Explanations

    phrases related to negative accusations or claims

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to allegations and accusations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uristic
    -0.81
    picture
    -0.81
    days
    -0.79
    minus
    -0.78
    izons
    -0.77
    wives
    -0.75
    terms
    -0.75
    iers
    -0.74
    keys
    -0.73
     partName
    -0.72
    POSITIVE LOGITS
     wrongdoing
    1.37
     misconduct
    1.23
     inacc
    1.20
     abuse
    1.15
     discrimination
    1.15
     vandalism
    1.13
     harassment
    1.12
     racism
    1.09
     fraud
    1.07
     criminality
    1.07
    Act Density 0.168%

    No Known Activations