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

    Neuronpedia

    INDEX
    Explanations

    phrases related to refusal or resistance

    oai_token-act-pair · gpt-3.5-turbo

    expressions of refusal or non-compliance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mingham
    -0.81
    è¦ļéĨĴ
    -0.76
    Ranked
    -0.72
    erno
    -0.71
    ########
    -0.70
    hetically
    -0.69
    wig
    -0.69
    utenberg
    -0.69
    oiler
    -0.68
    atures
    -0.66
    POSITIVE LOGITS
     to
    1.03
     admission
    0.92
     permission
    0.87
     invitations
    0.81
     requests
    0.79
     refunds
    0.79
     Admission
    0.77
     entry
    0.74
     payment
    0.73
     assistance
    0.73
    Act Density 0.035%

    No Known Activations