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

    Neuronpedia

    INDEX
    Explanations

    terms related to the review and editorial processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pard
    -0.21
    icode
    -0.17
    antu
    -0.17
    cool
    -0.14
    925
    -0.14
    gart
    -0.14
    ænd
    -0.14
    ñana
    -0.14
    Cool
    -0.14
    avigator
    -0.14
    POSITIVE LOGITS
    .SYSTEM
    0.15
     Peer
    0.15
    stadt
    0.15
     CASCADE
    0.14
    brig
    0.14
     cedar
    0.14
     uncomment
    0.14
    igne
    0.14
    oder
    0.14
    Anonymous
    0.14
    Act Density 0.007%

    No Known Activations