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

    Neuronpedia

    INDEX
    Explanations

    references to the word "Silver" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çķ
    -0.17
    688
    -0.15
    rac
    -0.15
    ergarten
    -0.15
    otec
    -0.14
    sj
    -0.14
     dp
    -0.14
    ParameterValue
    -0.13
     HEAD
    -0.13
    sis
    -0.13
    POSITIVE LOGITS
    ado
    0.26
     lining
    0.25
    ware
    0.24
    lining
    0.21
    ADO
    0.21
    mine
    0.20
    lake
    0.20
    -grey
    0.20
    stein
    0.20
    Silver
    0.19
    Act Density 0.009%

    No Known Activations