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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to user accounts and trust relationships in a specific platform

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æĺĮ
    -0.16
     transit
    -0.15
    658
    -0.15
    ť
    -0.15
     Hero
    -0.15
     Transit
    -0.14
     Hyde
    -0.14
     Nunes
    -0.14
     Crack
    -0.14
    kil
    -0.14
    POSITIVE LOGITS
     mood
    0.18
    IMS
    0.17
     Moodle
    0.17
     Mood
    0.17
    zon
    0.15
    CFG
    0.15
    -hooks
    0.15
    Guard
    0.15
     hooks
    0.14
    ainen
    0.14
    Act Density 0.006%

    No Known Activations