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

    Neuronpedia

    INDEX
    Explanations

    terms related to restrictions and limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    829
    -0.15
    029
    -0.14
    ister
    -0.13
    ην
    -0.13
    972
    -0.13
    omp
    -0.13
     Stanley
    -0.13
    ISTER
    -0.13
    Stan
    -0.13
     Wide
    -0.13
    POSITIVE LOGITS
    _presence
    0.23
     presence
    0.22
    Presence
    0.20
    presence
    0.19
    δα
    0.17
     inclusion
    0.16
     Presence
    0.16
    ials
    0.15
     ultimately
    0.15
     mixed
    0.15
    Act Density 0.008%

    No Known Activations