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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating capability or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    indent
    -0.17
     supposed
    -0.16
    rst
    -0.14
    ase
    -0.14
    ers
    -0.14
    ed
    -0.13
    ds
    -0.13
    èm
    -0.13
    ulfilled
    -0.13
    åĵ²
    -0.13
    POSITIVE LOGITS
    -bodied
    0.20
    ehir
    0.17
    NullException
    0.15
    tings
    0.15
    icut
    0.15
    à¥įसर
    0.15
    /disable
    0.15
    azar
    0.14
    atır
    0.14
    ilty
    0.14
    Act Density 0.059%

    No Known Activations