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

    Neuronpedia

    INDEX
    Explanations

    references to professional or social relationships among individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pruitt
    -0.16
    ople
    -0.15
    dden
    -0.14
    andle
    -0.14
    arden
    -0.14
    kara
    -0.14
    orida
    -0.14
    izzo
    -0.14
    oucher
    -0.13
    exter
    -0.13
    POSITIVE LOGITS
    hood
    0.21
    hip
    0.20
    ship
    0.20
    ships
    0.18
    们
    0.17
     whom
    0.17
    /part
    0.16
    /op
    0.16
    innen
    0.15
    hips
    0.15
    Act Density 0.120%

    No Known Activations