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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating emerging talent or potential

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ken
    -0.19
     upright
    -0.17
    -upload
    -0.17
    adar
    -0.16
     uplift
    -0.16
    987
    -0.16
    endif
    -0.15
     upwards
    -0.15
    alah
    -0.15
    upgrade
    -0.15
    POSITIVE LOGITS
    /down
    0.24
    ATAB
    0.19
    andan
    0.18
    æĹı
    0.17
     comer
    0.17
    coming
    0.16
    andas
    0.16
    sert
    0.16
    Coming
    0.16
     coming
    0.15
    Act Density 0.021%

    No Known Activations