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

    Neuronpedia

    INDEX
    Explanations

    references to ranks or status within a hierarchical system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ullam
    -0.15
    etri
    -0.15
    rema
    -0.15
    rud
    -0.15
    avr
    -0.14
    PROTO
    -0.14
    wort
    -0.14
    alez
    -0.14
    ient
    -0.14
    imson
    -0.14
    POSITIVE LOGITS
    coil
    0.15
    cas
    0.15
     htonl
    0.14
    ull
    0.14
    ULL
    0.14
    kov
    0.14
    OWER
    0.14
    мп
    0.14
     Cyber
    0.13
    ëıĮ
    0.13
    Act Density 0.019%

    No Known Activations