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

    Neuronpedia

    INDEX
    Explanations

    references to dual capabilities or features in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zeug
    -0.19
    esel
    -0.16
    est
    -0.15
    -vous
    -0.15
    essian
    -0.15
    liness
    -0.15
    esh
    -0.15
    emed
    -0.15
    ems
    -0.14
    LY
    -0.14
    POSITIVE LOGITS
    -purpose
    0.22
    ité
    0.18
    istic
    0.18
    ities
    0.17
    /single
    0.17
    licity
    0.17
     Ended
    0.17
    ityEngine
    0.16
    isme
    0.16
    ntity
    0.16
    Act Density 0.012%

    No Known Activations