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

    Neuronpedia

    INDEX
    Explanations

    relationships between previous research findings and their current applications or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idar
    -0.17
    vrier
    -0.15
    wu
    -0.15
    eya
    -0.15
     insol
    -0.14
    ICIAL
    -0.14
    friends
    -0.14
    FromClass
    -0.14
    .Hosting
    -0.14
     Sext
    -0.14
    POSITIVE LOGITS
    ç«
    0.15
    cast
    0.14
     Convers
    0.14
    atk
    0.14
    unct
    0.14
    tvrt
    0.13
    FINITY
    0.13
    castle
    0.13
    asu
    0.13
     Lamp
    0.13
    Act Density 0.084%

    No Known Activations