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

    Neuronpedia

    INDEX
    Explanations

    references to personal pronouns and their forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odo
    -0.17
    -fw
    -0.15
    avra
    -0.14
    _INITIALIZER
    -0.14
    iste
    -0.14
    TEGER
    -0.14
    AccessType
    -0.13
     üz
    -0.13
    ickers
    -0.13
    berger
    -0.13
    POSITIVE LOGITS
    alice
    0.17
    esus
    0.15
    -CN
    0.15
    edics
    0.14
    illard
    0.14
    alim
    0.14
    endency
    0.14
    eh
    0.14
     Kurd
    0.13
     Rolls
    0.13
    Act Density 0.123%

    No Known Activations