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

    Neuronpedia

    INDEX
    Explanations

    references to legal citations and legal documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    berman
    -0.20
    rum
    -0.15
    vert
    -0.14
    IMP
    -0.14
    581
    -0.13
    erg
    -0.13
    imbus
    -0.13
    ment
    -0.13
     gym
    -0.13
     Fuse
    -0.13
    POSITIVE LOGITS
    usch
    0.14
    åĶ±
    0.14
    uder
    0.14
    ELY
    0.14
    uden
    0.14
     Alo
    0.14
    ileo
    0.13
    ãĥ¼ãĥĦ
    0.13
    achte
    0.13
    _bases
    0.13
    Act Density 0.015%

    No Known Activations