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

    Neuronpedia

    INDEX
    Explanations

    expressions of betrayal and trust issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oble
    -0.18
    ovel
    -0.18
    Å¡i
    -0.16
    akash
    -0.16
    à¥ĭफ
    -0.15
    amt
    -0.15
    kir
    -0.14
    ocos
    -0.14
     Wa
    -0.14
     anonymously
    -0.14
    POSITIVE LOGITS
    quine
    0.15
     O
    0.15
    åŃĺäºİ
    0.15
    shaw
    0.15
    hai
    0.14
    /Dk
    0.14
     norge
    0.14
     Sim
    0.14
     sim
    0.14
    362
    0.14
    Act Density 0.096%

    No Known Activations