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

    Neuronpedia

    INDEX
    Explanations

    technical language related to mathematical functions and optimization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atars
    -0.16
     Duffy
    -0.15
    FRING
    -0.15
    aign
    -0.14
     UNU
    -0.14
    IFS
    -0.14
    iling
    -0.14
     snow
    -0.14
    quir
    -0.14
     заг
    -0.14
    POSITIVE LOGITS
     objective
    0.19
     Objective
    0.18
     objectives
    0.17
     Optimization
    0.16
    å¼ı
    0.16
    anja
    0.16
    gregator
    0.15
    loss
    0.15
    objective
    0.15
    Objective
    0.15
    Act Density 0.078%

    No Known Activations