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

    Neuronpedia

    INDEX
    Explanations

    phrases related to societal criticisms and discussions about historical injustices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    redient
    -0.57
    tiérrez
    -0.56
    InputBorder
    -0.56
     vastaan
    -0.56
    duled
    -0.55
    StoryboardSegue
    -0.54
    ulongan
    -0.54
    енча
    -0.53
    באנגלית
    -0.53
    Javadoc
    -0.53
    POSITIVE LOGITS
    ⓧ
    0.66
    发表于
    0.63
    its
    0.54
     [*]
    0.53
     okuyayım
    0.51
    CompilerServices
    0.51
    this
    0.50
    blob
    0.50
     Biôgrafia
    0.49
     funny
    0.48
    Act Density 0.221%

    No Known Activations