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

    Neuronpedia

    INDEX
    Explanations

    goals related to educational metrics and assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     undergraduate
    -0.20
     undergrad
    -0.18
    _fault
    -0.16
    RLF
    -0.15
     QS
    -0.15
    amon
    -0.14
    ziej
    -0.14
     赤
    -0.14
    azor
    -0.14
    ãģĭãģĹ
    -0.14
    POSITIVE LOGITS
     AP
    0.38
    AP
    0.30
     Dual
    0.27
    /AP
    0.26
    (AP
    0.26
     dual
    0.25
     Advanced
    0.24
     IB
    0.24
    Dual
    0.24
    .AP
    0.21
    Act Density 0.040%

    No Known Activations