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

    Neuronpedia

    INDEX
    Explanations

    important legal and advisory terms related to policy and caution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è±Ĭ
    -0.18
    ogenerated
    -0.16
     Ney
    -0.16
    º
    -0.15
    apı
    -0.15
    èī¯
    -0.14
    )arg
    -0.14
     ãĤ¹
    -0.14
     mach
    -0.14
    695
    -0.14
    POSITIVE LOGITS
    uron
    0.18
    urring
    0.16
     Le
    0.15
     Mt
    0.15
    @student
    0.15
    ur
    0.15
     Madagascar
    0.15
     Bundy
    0.15
    fet
    0.14
     Os
    0.14
    Act Density 0.043%

    No Known Activations