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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate quality or assessment of performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ³ãĥĨãĤ£
    -0.17
    807
    -0.15
    addin
    -0.15
    affer
    -0.15
    805
    -0.15
    ạng
    -0.14
    енÑĤÑĥ
    -0.14
    well
    -0.14
     Verfügung
    -0.14
    ragen
    -0.13
    POSITIVE LOGITS
     job
    0.30
    job
    0.24
     bang
    0.21
     ye
    0.20
     impression
    0.19
     Job
    0.19
    Job
    0.18
     impressions
    0.18
    -job
    0.18
    .job
    0.18
    Act Density 0.020%

    No Known Activations