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

    Neuronpedia

    INDEX
    Explanations

    instances of refusal or rejection to provide information or comments

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

    declined to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     дописавши
    -0.44
    Искәрмәләр
    -0.41
    RenderAtEndOf
    -0.41
    Portail
    -0.38
     suced
    -0.36
    érable
    -0.36
    MLLoader
    -0.36
    SUD
    -0.35
    sur
    -0.35
    TintMode
    -0.35
    POSITIVE LOGITS
     zwiſchen
    0.56
     imagui
    0.52
     poffe
    0.51
    rungsseite
    0.50
    tagHelperRunner
    0.50
    urtstag
    0.49
     témoig
    0.49
     Roskov
    0.49
     queſto
    0.49
    iſchen
    0.49
    Act Density 0.018%

    No Known Activations