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

    Neuronpedia

    INDEX
    Explanations

    references to physical locations and actions related to entering or being inside spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ansi
    -0.15
    oren
    -0.14
    iams
    -0.14
    ungan
    -0.14
    zos
    -0.14
    uish
    -0.14
    orgot
    -0.14
    опиÑģ
    -0.13
    hurst
    -0.13
    wert
    -0.13
    POSITIVE LOGITS
     Svens
    0.14
    WD
    0.14
    Wunused
    0.14
     lighten
    0.14
    adle
    0.13
    ets
    0.13
     Samar
    0.13
    samples
    0.13
     Kil
    0.13
     into
    0.13
    Act Density 0.119%

    No Known Activations