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

    Neuronpedia

    INDEX
    Explanations

    instances of the prefix "uns," indicating negativity or undesirability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HEET
    -0.16
    iena
    -0.16
    lexport
    -0.15
    emer
    -0.15
    AZE
    -0.15
    éĽĦ
    -0.15
    PLICIT
    -0.15
    BX
    -0.15
    .creation
    -0.14
    idence
    -0.14
    POSITIVE LOGITS
     uns
    0.20
     Uns
    0.20
    ung
    0.18
    avour
    0.18
    olicited
    0.18
    uguay
    0.17
    aturated
    0.17
    ull
    0.16
    at
    0.16
    plash
    0.15
    Act Density 0.006%

    No Known Activations