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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating inclusion or references to specific subsets or groups within a larger context

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

    amongst the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    @[+][
    -0.45
    ThroughAttribute
    -0.43
     beh
    -0.39
    ﾟ)
    -0.38
    istoitu
    -0.35
     spoiler
    -0.34
     sate
    -0.34
    edicated
    -0.34
     Alleg
    -0.33
     Souvenir
    -0.33
    POSITIVE LOGITS
     others
    0.88
     Others
    0.83
    Others
    0.79
     OTHERS
    0.70
    others
    0.69
     دیگران
    0.58
    AsUp
    0.56
     Vielfalt
    0.55
     many
    0.53
     Vielzahl
    0.53
    Act Density 0.014%

    No Known Activations