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

    Neuronpedia

    INDEX
    Explanations

    references to social interactions and personal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ecz
    -0.15
    amespace
    -0.15
    oran
    -0.15
    RTL
    -0.15
    oby
    -0.15
    nette
    -0.14
    icle
    -0.14
    cheon
    -0.13
     дÑĢа
    -0.13
    oria
    -0.13
    POSITIVE LOGITS
    ollo
    0.16
     Handlers
    0.14
    boro
    0.14
    iam
    0.14
    ilir
    0.14
    quine
    0.13
    375
    0.13
     Booker
    0.13
    esson
    0.13
    arkan
    0.13
    Act Density 0.093%

    No Known Activations