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

    Neuronpedia

    INDEX
    Explanations

    phrases related to threats and intimidation

    oai_token-act-pair · gpt-3.5-turbo

    references to threats and complaints, particularly involving harassment and requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bip
    -0.72
    arist
    -0.71
    illac
    -0.70
     tripod
    -0.68
    icz
    -0.66
     ESV
    -0.65
    hess
    -0.65
    sonian
    -0.64
    coat
    -0.64
     PBS
    -0.64
    POSITIVE LOGITS
    mith
    0.92
     mailed
    0.90
    olicited
    0.89
     emanating
    0.85
    uggest
    0.83
     requests
    0.82
     solicitation
    0.81
     directed
    0.80
    pring
    0.80
     totaling
    0.80
    Act Density 0.272%

    No Known Activations