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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values associated with authors and publication details in academic references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    STM
    -0.15
    urv
    -0.15
    ekte
    -0.14
    anzi
    -0.14
    .cmb
    -0.14
    zier
    -0.14
    .nlm
    -0.14
    оÑĤи
    -0.14
    enburg
    -0.14
    STA
    -0.14
    POSITIVE LOGITS
     ab
    0.15
    loat
    0.14
     Polly
    0.14
    xFFF
    0.14
     Pis
    0.13
     dev
    0.13
     hor
    0.13
    _named
    0.13
     dem
    0.13
     b
    0.13
    Act Density 0.003%

    No Known Activations