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

    Neuronpedia

    INDEX
    Explanations

    scientific terminology and concepts related to algorithms and data analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pulse
    -0.16
    oproject
    -0.15
     UIControl
    -0.14
    OffsetTable
    -0.14
     Cosmos
    -0.14
     pulse
    -0.14
    ervals
    -0.14
    utely
    -0.13
    _Osc
    -0.13
    quarter
    -0.13
    POSITIVE LOGITS
    Bay
    0.30
     bay
    0.29
     Bay
    0.29
     latent
    0.29
     posterior
    0.29
     Bayesian
    0.28
    bay
    0.27
     likelihood
    0.26
     marginalized
    0.24
     poster
    0.24
    Act Density 0.023%

    No Known Activations