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

    Neuronpedia

    INDEX
    Explanations

    instances of refusal or denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Refusal or declination of something

    np_acts-logits-general · gemini-2.0-flash

    refused to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Somebody
    -0.57
     فريبيس
    -0.56
    Someone
    -0.54
     Someone
    -0.53
    somewhere
    -0.53
     tikai
    -0.53
    Either
    -0.49
    someone
    -0.47
    ържа
    -0.47
     Either
    -0.46
    POSITIVE LOGITS
     any
    1.01
     altogether
    0.86
     catég
    0.86
     temptation
    0.79
    AddTagHelper
    0.77
     further
    0.76
     hẳn
    0.76
     unnecessary
    0.71
     любые
    0.71
    any
    0.71
    Act Density 0.362%

    No Known Activations