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

    Neuronpedia

    INDEX
    Explanations

    instances of measures related to safety and protection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Away
    -0.15
    Away
    -0.14
    084
    -0.14
    085
    -0.14
     output
    -0.14
     تب
    -0.14
    otal
    -0.14
    ields
    -0.13
     away
    -0.13
     outputs
    -0.13
    POSITIVE LOGITS
     enter
    0.83
     entering
    0.79
     enters
    0.79
     entered
    0.77
    enter
    0.75
     Enter
    0.71
     entry
    0.71
    -enter
    0.69
    è¿Ľåħ¥
    0.68
    Enter
    0.68
    Act Density 0.403%

    No Known Activations