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

    Neuronpedia

    INDEX
    Explanations

    phrases or expressions related to endings or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pressured
    -0.17
    bedo
    -0.16
    nal
    -0.15
    bag
    -0.14
    bags
    -0.14
    inen
    -0.14
    ften
    -0.13
    éf
    -0.13
    ington
    -0.13
    828
    -0.13
    POSITIVE LOGITS
    eh
    0.15
    went
    0.14
    QE
    0.14
     Situation
    0.14
     Laf
    0.14
    aina
    0.14
    éī
    0.14
     Bison
    0.13
    TEGER
    0.13
    boss
    0.13
    Act Density 0.011%

    No Known Activations