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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditionality or stipulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.58
     SafeMath
    -0.56
    oskop
    -0.54
    avu
    -0.53
    OptionsMenu
    -0.53
    ModelSerializer
    -0.52
    GEBURTSDATUM
    -0.52
     Vikipedi
    -0.50
    LLocation
    -0.50
    irchen
    -0.50
    POSITIVE LOGITS
     Roskov
    0.55
     تانيه
    0.52
    īts
    0.51
     gebru
    0.51
     dAtA
    0.50
     Wikimedijinoj
    0.50
    __(/*!
    0.50
     curé
    0.49
    RegistryLite
    0.49
     olev
    0.48
    Act Density 0.484%

    No Known Activations