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

    Neuronpedia

    INDEX
    Explanations

    words related to conflicts or disagreements, particularly in social and political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etti
    -0.20
    etri
    -0.14
    edula
    -0.14
     âĨĴ↵↵
    -0.14
     sip
    -0.14
    tti
    -0.14
    BOSE
    -0.14
    esen
    -0.14
    ÙħÙĨد
    -0.14
    _ACTIVE
    -0.14
    POSITIVE LOGITS
    anj
    0.20
    hol
    0.17
    ýt
    0.16
    aq
    0.16
    ats
    0.16
    ãĥ³ãĥĢ
    0.15
    δα
    0.15
    icom
    0.15
     Intermediate
    0.15
    els
    0.15
    Act Density 0.018%

    No Known Activations