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

    Neuronpedia

    INDEX
    Explanations

    references to geographical locations and natural attractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rais
    -0.17
    andalone
    -0.16
    Pow
    -0.16
    gem
    -0.15
     Herz
    -0.15
     veloc
    -0.15
    igest
    -0.15
    gel
    -0.14
     Pow
    -0.14
     ÙħÙħÙĨ
    -0.14
    POSITIVE LOGITS
    Ñħодим
    0.15
    Å¡k
    0.14
     è±
    0.14
    ulas
    0.14
     Entre
    0.14
    inka
    0.13
     spins
    0.13
    EDGE
    0.13
    spinner
    0.13
    MBER
    0.13
    Act Density 0.010%

    No Known Activations