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

    Neuronpedia

    INDEX
    Explanations

    instances of dialog and interactions between characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CTS
    -0.16
    ÙĪØ·
    -0.15
    trap
    -0.14
    éro
    -0.14
    ehr
    -0.14
    ãĥ¼ãĥģ
    -0.14
    chet
    -0.14
     frustr
    -0.14
     Dün
    -0.14
    aby
    -0.14
    POSITIVE LOGITS
     immediately
    0.30
     immediate
    0.27
     instantly
    0.26
     reaction
    0.26
     reactions
    0.25
     immedi
    0.23
     react
    0.23
     Immediately
    0.22
     initially
    0.22
     reacts
    0.21
    Act Density 0.439%

    No Known Activations