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

    Neuronpedia

    INDEX
    Explanations

    terms related to identity and representation within social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CK
    -0.14
    DG
    -0.14
    ạ
    -0.14
    bons
    -0.14
     mess
    -0.14
    Ø·ÙĪر
    -0.14
    ouns
    -0.13
    oun
    -0.13
    iedy
    -0.13
     Carlson
    -0.13
    POSITIVE LOGITS
    parity
    0.16
    .metamodel
    0.16
    å¢
    0.15
    nable
    0.14
    dao
    0.14
    åķ
    0.14
    ura
    0.14
    UPLE
    0.13
    _drvdata
    0.13
     Potter
    0.13
    Act Density 0.000%

    No Known Activations