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

    Neuronpedia

    INDEX
    Explanations

    key concepts or terms related to arguments and their justifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙĪØ©
    -0.15
     Anim
    -0.14
     autogenerated
    -0.14
    pu
    -0.13
    ember
    -0.13
    anj
    -0.13
    eton
    -0.13
    oki
    -0.13
     Ember
    -0.13
    ¤
    -0.13
    POSITIVE LOGITS
    ileo
    0.15
    Evt
    0.15
    erot
    0.15
    mux
    0.14
     Alma
    0.14
    pel
    0.14
    ammers
    0.14
    Îŀ
    0.14
    رÙĬد
    0.14
    acades
    0.14
    Act Density 0.007%

    No Known Activations