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

    Neuronpedia

    INDEX
    Explanations

    themes of power dynamics and complex emotional relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     jadx
    -0.17
    nodoc
    -0.16
    Recovered
    -0.16
    dek
    -0.15
     Sheridan
    -0.15
    æĭ©
    -0.15
     servisi
    -0.15
    _drop
    -0.14
    æ³Ĭ
    -0.14
    _authenticated
    -0.14
    POSITIVE LOGITS
     Pur
    0.15
     tolerance
    0.15
    oller
    0.15
    æĺĮ
    0.15
    aval
    0.14
     Salv
    0.14
     displacement
    0.13
    ocrates
    0.13
     held
    0.13
    aida
    0.13
    Act Density 0.211%

    No Known Activations