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

    Neuronpedia

    INDEX
    Explanations

    concepts related to pride and self-expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gaard
    -0.15
    ifar
    -0.15
    geois
    -0.14
    rei
    -0.14
    Ðİ
    -0.14
    ENCY
    -0.14
    PLL
    -0.14
     yourselves
    -0.14
    onth
    -0.14
    swith
    -0.13
    POSITIVE LOGITS
     his
    0.38
     its
    0.37
     sua
    0.36
     seus
    0.34
     their
    0.34
     suas
    0.33
     seu
    0.30
     suoi
    0.30
     suo
    0.29
     jego
    0.28
    Act Density 0.469%

    No Known Activations