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

    Neuronpedia

    INDEX
    Explanations

    contractions and possessive forms of pronouns indicating relationships or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    486
    -0.17
    oster
    -0.16
    haus
    -0.15
     ÙĤØ·
    -0.15
    iance
    -0.15
    itz
    -0.14
    orz
    -0.14
    iac
    -0.13
    311
    -0.13
    42
    -0.13
    POSITIVE LOGITS
     ApplicationException
    0.17
    estar
    0.17
    uria
    0.16
    aya
    0.15
    egis
    0.15
    estre
    0.15
    اسطة
    0.15
    aida
    0.14
    _WARN
    0.14
    \application
    0.14
    Act Density 0.148%

    No Known Activations