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

    Neuronpedia

    INDEX
    Explanations

    elements indicating group identity and collective beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thasone
    -0.33
    therners
    -0.33
     réparer
    -0.31
     iprot
    -0.30
    intervento
    -0.29
     peruan
    -0.29
     Bruno
    -0.28
     étranger
    -0.28
     szko
    -0.28
    ífica
    -0.28
    POSITIVE LOGITS
    aarrggbb
    0.63
     المعيارى
    0.59
     snippetHide
    0.58
    сылкі
    0.56
    RotationOrder
    0.51
     linkovi
    0.51
    rinfo
    0.50
    fromnode
    0.49
    PostInfinity
    0.49
     '\\;'
    0.48
    Act Density 0.138%

    No Known Activations