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

    Neuronpedia

    INDEX
    Explanations

    technical terminology related to system performance and development in the context of research and innovation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     programme
    -0.16
    èĨľ
    -0.15
    [at
    -0.14
     programmes
    -0.14
    itting
    -0.13
    utron
    -0.13
    å¯Ħ
    -0.13
     international
    -0.13
    [it
    -0.13
    ren
    -0.13
    POSITIVE LOGITS
     leveraging
    0.22
     w
    0.22
     conditioned
    0.19
     lever
    0.19
     trained
    0.18
     leverage
    0.17
     conditioning
    0.17
     learned
    0.17
     capturing
    0.16
     pretrained
    0.16
    Act Density 0.124%

    No Known Activations