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

    Neuronpedia

    INDEX
    Explanations

    conversational expressions and statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ancell
    -0.18
    opard
    -0.15
     padd
    -0.15
    iação
    -0.15
    iar
    -0.15
    tha
    -0.14
    aday
    -0.14
    楼
    -0.14
     paddle
    -0.14
    ainter
    -0.14
    POSITIVE LOGITS
     rein
    0.17
    stamp
    0.15
    -ng
    0.14
    SPELL
    0.14
    uhn
    0.14
     Bren
    0.14
     jean
    0.14
     cert
    0.14
    ué
    0.14
    ë§IJ
    0.14
    Act Density 0.035%

    No Known Activations