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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating awards or recognitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mps
    -0.18
    ±Ð¾ÑĤ
    -0.16
     Whit
    -0.16
    evi
    -0.15
    Äįer
    -0.14
     nackte
    -0.14
     forks
    -0.14
    gii
    -0.14
    ijke
    -0.14
    ayo
    -0.14
    POSITIVE LOGITS
    (Optional
    0.15
    903
    0.13
     Pane
    0.13
    CBC
    0.13
    geb
    0.13
    iore
    0.13
     respective
    0.13
     Enum
    0.13
     MyApp
    0.13
    reib
    0.13
    Act Density 0.017%

    No Known Activations