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

    Neuronpedia

    INDEX
    Explanations

    instances of physical entrapment or confinement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    E
    -0.15
     Preview
    -0.15
    undred
    -0.15
     predict
    -0.14
    üt
    -0.14
     Wyn
    -0.14
     Crown
    -0.14
    strup
    -0.14
    elay
    -0.14
    ea
    -0.14
    POSITIVE LOGITS
    èĨ
    0.17
    ãĥ³ãĥĨ
    0.16
    insk
    0.16
    alet
    0.15
    ÙĪبÛĮ
    0.15
    eyse
    0.15
    ÐŁÐļ
    0.15
    WND
    0.15
    orig
    0.14
    hlen
    0.14
    Act Density 0.346%

    No Known Activations