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

    Neuronpedia

    INDEX
    Explanations

    terms relating to softening, mitigating, or cushioning effects in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ÙĤائÙħØ©
    -0.17
    ehler
    -0.15
    aul
    -0.15
    anness
    -0.15
    iye
    -0.15
    debit
    -0.14
    orders
    -0.14
    omain
    -0.14
    ains
    -0.14
     Orders
    -0.14
    POSITIVE LOGITS
    .Parcelable
    0.17
    vala
    0.16
    èģĶ
    0.15
    uls
    0.15
     Voor
    0.15
    еÑĢо
    0.15
    ród
    0.15
    icros
    0.14
     Serialized
    0.14
     prere
    0.13
    Act Density 0.116%

    No Known Activations