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

    Neuronpedia

    INDEX
    Explanations

    references to relationships and emotional connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eldon
    -0.15
    hes
    -0.15
    gers
    -0.14
     Fred
    -0.14
    unden
    -0.14
    wend
    -0.14
    OwnProperty
    -0.14
    elden
    -0.14
    èº
    -0.14
    Dos
    -0.14
    POSITIVE LOGITS
    SEE
    0.16
    nev
    0.14
    utch
    0.14
    409
    0.14
    fare
    0.13
     description
    0.13
     fleet
    0.13
     möchten
    0.13
    trap
    0.13
    spiracy
    0.13
    Act Density 0.130%

    No Known Activations