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

    Neuronpedia

    INDEX
    Explanations

    demonstrative pronouns indicating specificity or reference

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

    introduces specific items or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bilde
    -0.32
     Pat
    -0.31
    È
    -0.31
     Hage
    -0.30
     discussions
    -0.30
    group
    -0.29
    ợn
    -0.29
    pat
    -0.29
    ere
    -0.28
     Group
    -0.28
    POSITIVE LOGITS
    ſelf
    0.77
    AddTagHelper
    0.73
     myſelf
    0.69
    ThroughAttribute
    0.63
    存于互联网档案馆
    0.62
     Theſe
    0.60
    ]")]
    0.60
     ſte
    0.59
    "],
    0.59
     queſta
    0.57
    Act Density 0.045%

    No Known Activations