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

    Neuronpedia

    INDEX
    Explanations

    numerical references related to statistics or figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ourn
    -0.15
     ramp
    -0.14
    my
    -0.14
    ea
    -0.14
    anything
    -0.14
    Enum
    -0.14
    bp
    -0.14
    heck
    -0.14
    usch
    -0.13
    hoot
    -0.13
    POSITIVE LOGITS
    chter
    0.16
    iamond
    0.14
    uerdo
    0.14
    ãĤ¤ãĥ³ãĥĪ
    0.14
    orld
    0.14
    uger
    0.14
    úc
    0.14
    oux
    0.14
    ì²´
    0.14
     Marks
    0.14
    Act Density 0.080%

    No Known Activations