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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of imprisonment or confinement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oldem
    -0.18
    ãĥĥãĥĦ
    -0.16
     maduras
    -0.14
    goto
    -0.14
    bud
    -0.14
    λει
    -0.14
    enderit
    -0.14
    chte
    -0.14
    akukan
    -0.14
    argo
    -0.13
    POSITIVE LOGITS
     becomes
    0.44
     become
    0.37
    bec
    0.32
     became
    0.30
     suddenly
    0.28
     Become
    0.28
     Suddenly
    0.28
     Became
    0.27
    uddenly
    0.26
     ÑģÑĤановиÑĤÑģÑı
    0.25
    Act Density 0.341%

    No Known Activations