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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific government bodies or officials

    oai_token-act-pair · gpt-3.5-turbo

    references to states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    angelo
    -0.65
    bear
    -0.63
    KT
    -0.63
    epad
    -0.62
    iator
    -0.62
    Reference
    -0.61
    JECT
    -0.61
    GUI
    -0.61
    Editor
    -0.61
    editor
    -0.61
    POSITIVE LOGITS
     tallest
    0.89
     own
    0.86
     premier
    0.84
    selves
    0.83
     largest
    0.81
     finest
    0.78
     shores
    0.78
     landmark
    0.78
     newest
    0.78
     poorest
    0.78
    Act Density 0.111%

    No Known Activations