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

    Neuronpedia

    INDEX
    Explanations

    references to identity and personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stown
    -0.19
    tracker
    -0.15
     Coff
    -0.15
    еÑĢж
    -0.15
    atha
    -0.15
    aphore
    -0.15
    ERTICAL
    -0.15
    etto
    -0.14
    strict
    -0.14
    ahoma
    -0.14
    POSITIVE LOGITS
    herits
    0.18
    ddl
    0.15
    enan
    0.14
     Inspiration
    0.13
    orns
    0.13
    umat
    0.13
     Mana
    0.13
    _OD
    0.13
    ugar
    0.13
    θεν
    0.13
    Act Density 0.107%

    No Known Activations