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

    Neuronpedia

    INDEX
    Explanations

    terms related to understanding and privacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Unchecked
    -0.40
     lock
    -0.36
    geführt
    -0.35
     Dale
    -0.35
    ご了承ください
    -0.33
     perpetually
    -0.33
     Moreira
    -0.31
    IntoConstraints
    -0.31
    Karriere
    -0.31
     monitor
    -0.31
    POSITIVE LOGITS
    UnitTesting
    0.75
     surla
    0.64
    TargetException
    0.54
     autorytatywna
    0.52
     fubject
    0.52
    PyExc
    0.52
    IsMutable
    0.51
    fjspx
    0.50
    setVerticalGroup
    0.50
     writeTo
    0.49
    Act Density 0.130%

    No Known Activations