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

    Neuronpedia

    INDEX
    Explanations

    instructional content related to self-defense and safety training

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è«
    -0.17
    леÑĩ
    -0.14
    nable
    -0.14
    ofire
    -0.14
     veren
    -0.13
     strSql
    -0.13
    ControlEvents
    -0.13
     automáticamente
    -0.13
    Ø´Ùģ
    -0.13
    eless
    -0.13
    POSITIVE LOGITS
     how
    0.29
     basic
    0.27
     basics
    0.27
    å¦Ĥä½ķ
    0.27
     tips
    0.25
    basic
    0.23
    how
    0.23
     proper
    0.23
     effective
    0.23
     techniques
    0.22
    Act Density 0.178%

    No Known Activations