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

    Neuronpedia

    INDEX
    Explanations

    terms related to safety and security measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jamb
    -0.71
     ImGui
    -0.62
    quelize
    -0.61
    irmanship
    -0.59
     Gim
    -0.58
    .$.
    -0.58
     gim
    -0.58
     Arrondissement
    -0.58
    Subviews
    -0.57
    کان
    -0.57
    POSITIVE LOGITS
     protection
    2.15
     Protection
    2.02
     protects
    2.01
     protect
    1.99
     Protect
    1.97
     protections
    1.94
    Protect
    1.92
     PROTECT
    1.90
    protection
    1.89
    Protection
    1.89
    Act Density 0.082%

    No Known Activations