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

    Neuronpedia

    INDEX
    Explanations

    references to user policies and resources in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Straight
    -0.14
    ameleon
    -0.14
    bin
    -0.14
    eshire
    -0.14
    ummer
    -0.14
     straight
    -0.14
    ctl
    -0.14
     Wak
    -0.14
    criptions
    -0.14
    ÐĽÐ¬
    -0.14
    POSITIVE LOGITS
    Ïģιν
    0.15
    agal
    0.14
    acier
    0.14
     @$_
    0.14
    dech
    0.14
    åı£
    0.14
    acios
    0.13
    ãģĿãģĹãģ¦
    0.13
     Buccane
    0.13
    .Xml
    0.13
    Act Density 0.388%

    No Known Activations