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

    Neuronpedia

    INDEX
    Explanations

    references to interpersonal relationships and conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PELL
    -0.18
    isÃŃ
    -0.16
    mitt
    -0.16
    ñana
    -0.15
    «ĺ
    -0.15
    antity
    -0.15
    tera
    -0.15
    InputElement
    -0.15
     POSSIBILITY
    -0.14
    Stores
    -0.14
    POSITIVE LOGITS
     Closure
    0.15
    avern
    0.15
    fin
    0.15
     Eaton
    0.15
     Cab
    0.15
     hold
    0.14
    ais
    0.14
     Erica
    0.14
    erner
    0.14
     Morales
    0.14
    Act Density 0.094%

    No Known Activations