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

    Neuronpedia

    INDEX
    Explanations

    terms related to emotions or feelings of guilt and resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uez
    -0.16
    otation
    -0.16
     serg
    -0.15
    olit
    -0.15
    kok
    -0.15
    Encoded
    -0.14
    lotte
    -0.14
    ãģ¨ãģ®
    -0.14
    uki
    -0.14
    eration
    -0.14
    POSITIVE LOGITS
    edBy
    0.21
    itably
    0.20
    ceeded
    0.17
    inally
    0.17
    ován
    0.17
    aneously
    0.16
    jang
    0.16
    efully
    0.15
    alyzed
    0.15
    ically
    0.15
    Act Density 0.357%

    No Known Activations