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

    Neuronpedia

    INDEX
    Explanations

    references to experimental data and methodologies in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nan
    -0.16
     Spaces
    -0.14
     Casual
    -0.14
     Emerald
    -0.14
    hil
    -0.14
     casual
    -0.14
    amo
    -0.14
     Instances
    -0.14
     Pearl
    -0.14
    timeofday
    -0.13
    POSITIVE LOGITS
     Shower
    0.21
     shower
    0.20
     Cousins
    0.20
    GeV
    0.19
     veto
    0.19
     calor
    0.18
     fit
    0.18
    TeV
    0.17
     Liver
    0.17
     showers
    0.17
    Act Density 0.006%

    No Known Activations