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

    Neuronpedia

    INDEX
    Explanations

    verbs related to taking action or making changes

    oai_token-act-pair · gpt-3.5-turbo

    references to implementing or enacting changes or policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ubi
    -0.76
     istg
    -0.72
    INFO
    -0.72
    Represent
    -0.64
    enery
    -0.63
    feld
    -0.61
    Rus
    -0.61
    pring
    -0.61
    ahoo
    -0.61
    tub
    -0.60
    POSITIVE LOGITS
     policies
    1.18
     reforms
    1.12
     stricter
    1.11
     measures
    0.99
     safeguards
    0.97
     strategies
    0.96
     stringent
    0.94
     corrective
    0.92
     recommendations
    0.92
     regulations
    0.89
    Act Density 0.103%

    No Known Activations