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

    Neuronpedia

    INDEX
    Explanations

    mentions of repealing or canceling laws or regulations

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of repeal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiActiveUnfocused
    -0.97
     Harrington
    -0.70
    doms
    -0.67
     OPS
    -0.65
    heid
    -0.63
     Fraser
    -0.62
     seas
    -0.62
     Improvement
    -0.61
     Ops
    -0.60
     Io
    -0.60
    POSITIVE LOGITS
    aters
    1.29
    ating
    1.23
    ety
    1.16
    lling
    1.15
    ated
    1.11
    ater
    1.11
    issance
    1.06
    eter
    1.03
    aling
    1.00
    encer
    0.99
    Act Density 0.024%

    No Known Activations