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

    Neuronpedia

    INDEX
    Explanations

    terms relating to mechanisms and processes within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unan
    -0.19
    andy
    -0.18
    ñana
    -0.16
    .listView
    -0.16
    جÙħ
    -0.16
    pector
    -0.15
    rott
    -0.15
    agi
    -0.15
    aku
    -0.14
    ór
    -0.14
    POSITIVE LOGITS
     mechanisms
    0.17
     mechanism
    0.17
     underlying
    0.17
    uality
    0.17
    hift
    0.16
    /Instruction
    0.15
    urnal
    0.15
    atics
    0.15
    ologies
    0.15
    Ļ
    0.15
    Act Density 0.016%

    No Known Activations