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

    Neuronpedia

    INDEX
    Explanations

    references to influence and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    دÙĬØ«
    -0.16
    ãĥŃãĥ¼
    -0.16
    ildo
    -0.15
    #
    -0.15
    GGLE
    -0.15
    .started
    -0.14
    aldo
    -0.14
     bod
    -0.14
    utters
    -0.13
     deser
    -0.13
    POSITIVE LOGITS
     signs
    0.18
    alle
    0.18
     bare
    0.18
     Signs
    0.17
    rooms
    0.16
    (show
    0.16
     how
    0.16
     face
    0.15
    -lat
    0.14
    bare
    0.14
    Act Density 0.139%

    No Known Activations