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

    Neuronpedia

    INDEX
    Explanations

    expressions and terms related to disappointment and disillusionment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Geb
    -0.16
    igg
    -0.16
     Glas
    -0.15
     Viv
    -0.15
     Zah
    -0.14
    reich
    -0.14
    caa
    -0.14
    itt
    -0.14
    URE
    -0.14
    vida
    -0.14
    POSITIVE LOGITS
    heart
    0.29
    pir
    0.24
     heart
    0.21
    concert
    0.21
    -heart
    0.19
    quiet
    0.19
     appointment
    0.18
    Heart
    0.18
    lik
    0.17
     appoint
    0.17
    Act Density 0.016%

    No Known Activations