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

    Neuronpedia

    INDEX
    Explanations

    numerical values associated with various identifiers and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     medi
    -0.17
    utan
    -0.15
    rite
    -0.15
    AllowAnonymous
    -0.14
    getResponse
    -0.14
    oucher
    -0.14
     пÑĢавда
    -0.14
     ult
    -0.14
    uco
    -0.14
     haus
    -0.14
    POSITIVE LOGITS
    statt
    0.15
    umlu
    0.15
     TOR
    0.15
    idon
    0.14
     Field
    0.14
    asiswa
    0.14
    illed
    0.14
     Chronicle
    0.14
    ylie
    0.14
     Citizen
    0.14
    Act Density 0.563%

    No Known Activations