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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating recommendations or suggestions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irk
    -0.18
    enso
    -0.16
    /string
    -0.15
    rts
    -0.14
    irs
    -0.14
    .Invariant
    -0.14
    rz
    -0.14
    _transient
    -0.14
    è¿Ļä¹Ī
    -0.14
    å£ģ
    -0.14
    POSITIVE LOGITS
     too
    0.18
     particular
    0.16
     ÑĤоже
    0.16
     aspect
    0.15
     likewise
    0.15
    æĺĮ
    0.14
    /graphql
    0.14
     ebenfalls
    0.14
    throp
    0.14
    ook
    0.14
    Act Density 0.138%

    No Known Activations