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

    Neuronpedia

    INDEX
    Explanations

    terms related to reactions and responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oose
    -0.15
    kits
    -0.15
    rij
    -0.15
    passwd
    -0.15
    esen
    -0.15
    enza
    -0.15
    oya
    -0.15
    икÑĥ
    -0.14
    ucc
    -0.14
    ãĥ¼ãĥ
    -0.14
    POSITIVE LOGITS
    ivate
    0.39
    aries
    0.28
    ively
    0.24
    /react
    0.21
    iveness
    0.21
    ives
    0.20
    ual
    0.20
    ants
    0.19
    /response
    0.19
    ivated
    0.18
    Act Density 0.016%

    No Known Activations