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

    Neuronpedia

    INDEX
    Explanations

    words or phrases that indicate personal possession or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chwitz
    -0.16
    ırak
    -0.15
    oola
    -0.15
    ίγ
    -0.15
    buah
    -0.15
    AZY
    -0.15
    upil
    -0.15
    ẽ
    -0.14
    entiful
    -0.14
    äh
    -0.14
    POSITIVE LOGITS
     Beat
    0.16
     so
    0.15
     Wolff
    0.14
    amm
    0.14
     solvent
    0.14
     Freeze
    0.14
     Dot
    0.14
     Pale
    0.14
    cdn
    0.14
     miss
    0.14
    Act Density 0.027%

    No Known Activations