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

    Neuronpedia

    INDEX
    Explanations

    mentions of close relationships and intimacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orsch
    -0.16
    jak
    -0.16
    Aws
    -0.15
    èµ·ãģĵ
    -0.15
    ello
    -0.15
    atee
    -0.15
    IFIC
    -0.15
    entric
    -0.15
     Aviv
    -0.15
    üstü
    -0.14
    POSITIVE LOGITS
     proximity
    0.27
     knit
    0.23
    /close
    0.23
    -caption
    0.22
     clos
    0.21
    (close
    0.21
    close
    0.20
     close
    0.20
    -quarters
    0.19
     Close
    0.19
    Act Density 0.026%

    No Known Activations