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

    Neuronpedia

    INDEX
    Explanations

    references to reality television shows and competitive formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ADDE
    -0.19
    nech
    -0.16
    InputElement
    -0.16
    /Dk
    -0.15
    urate
    -0.15
    untas
    -0.15
    ANTE
    -0.15
    etz
    -0.15
    UTE
    -0.14
    KD
    -0.14
    POSITIVE LOGITS
    iten
    0.17
    emen
    0.15
     Martins
    0.15
    ave
    0.14
    arden
    0.14
     Reality
    0.14
     reality
    0.14
     Harding
    0.13
    isma
    0.13
     realities
    0.13
    Act Density 0.061%

    No Known Activations