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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating capability or potential actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arshal
    -0.13
    acades
    -0.13
    raud
    -0.13
    ds
    -0.13
    icamente
    -0.13
    ANJI
    -0.13
    libraries
    -0.13
    ãĤ¤ãĥ³ãĥĪ
    -0.12
    inee
    -0.12
    èm
    -0.12
    POSITIVE LOGITS
    -bodied
    0.22
    NullException
    0.16
    /disable
    0.15
    oire
    0.15
    iosk
    0.15
    tings
    0.14
    ãĤ·ãĥ¼
    0.14
    adians
    0.14
    γή
    0.14
    SID
    0.14
    Act Density 0.038%

    No Known Activations