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

    Neuronpedia

    INDEX
    Explanations

    terms related to online interactions and community engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    auen
    -0.18
    indle
    -0.17
    itol
    -0.17
     Vaults
    -0.17
    /Runtime
    -0.17
    abol
    -0.16
    atern
    -0.15
    evin
    -0.15
    iple
    -0.15
    antity
    -0.15
    POSITIVE LOGITS
     designated
    0.15
     forward
    0.15
     fan
    0.15
     Hil
    0.14
     Fan
    0.14
     Hubb
    0.14
     conc
    0.14
    744
    0.14
     arts
    0.13
    aby
    0.13
    Act Density 0.021%

    No Known Activations