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

    Neuronpedia

    INDEX
    Explanations

    organizations and their names or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quine
    -0.15
    tet
    -0.15
    lems
    -0.15
    orate
    -0.15
    Äĥm
    -0.15
     squir
    -0.14
    erea
    -0.14
    pire
    -0.14
    agua
    -0.14
    oped
    -0.14
    POSITIVE LOGITS
     fort
    0.14
     shock
    0.13
     Nero
    0.13
     Discipline
    0.13
     discipline
    0.13
     soft
    0.13
     pregnancy
    0.13
    54
    0.13
     Belt
    0.13
    é
    0.13
    Act Density 0.752%

    No Known Activations