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

    Neuronpedia

    INDEX
    Explanations

    references to historical figures or texts

    oai_token-act-pair · gpt-3.5-turbo

    the end of a document or text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     interns
    -0.87
     inputs
    -0.84
     backdoor
    -0.81
     TSA
    -0.80
     lasers
    -0.79
     Intercept
    -0.79
     waivers
    -0.78
     monitors
    -0.77
     triggers
    -0.77
     rollout
    -0.77
    POSITIVE LOGITS
    æ
    1.30
    ocrates
    1.25
    û
    1.20
    á¸
    1.18
    â
    1.17
    olkien
    1.15
    akespe
    1.14
    ospels
    1.14
    Å
    1.13
    Åį
    1.11
    Act Density 0.374%

    No Known Activations