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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating issues of security, legality, and the consequences of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arius
    -0.15
    ifton
    -0.15
    人æ°Ĺ
    -0.15
    çį²
    -0.14
    afka
    -0.14
    erin
    -0.14
    ilim
    -0.14
    olt
    -0.14
    ieber
    -0.14
    Toe
    -0.14
    POSITIVE LOGITS
    ien
    0.19
     Kens
    0.15
    itz
    0.15
    γκα
    0.15
     abs
    0.15
    Render
    0.15
     Rendering
    0.15
    RAIN
    0.15
    ihan
    0.15
     èª
    0.14
    Act Density 0.005%

    No Known Activations