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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a position or state of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /goto
    -0.16
    antz
    -0.15
    chia
    -0.14
    chk
    -0.14
    FLASH
    -0.14
    eday
    -0.14
    ãĤ¤ãĥ³ãĥĪ
    -0.14
    ustos
    -0.14
    addock
    -0.14
     cited
    -0.14
    POSITIVE LOGITS
    ãĤ¡
    0.17
    opis
    0.15
    ilot
    0.15
    ollider
    0.15
    .lib
    0.15
    iffer
    0.15
     Oscar
    0.14
     Pride
    0.14
    448
    0.14
    948
    0.14
    Act Density 0.016%

    No Known Activations