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

    Neuronpedia

    INDEX
    Explanations

    verbs related to causing destruction or significant impact

    oai_token-act-pair · gpt-3.5-turbo

    terms related to destruction or overwhelming actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LOS
    -0.73
    bringer
    -0.72
    fulness
    -0.64
    rock
    -0.64
    MY
    -0.62
    BOOK
    -0.62
    ford
    -0.62
    âĺħâĺħ
    -0.61
     LCS
    -0.60
     rein
    -0.59
    POSITIVE LOGITS
    ated
    2.60
    ating
    2.60
    ates
    2.25
    ation
    2.25
    ators
    2.24
    ate
    2.21
    ations
    2.18
    ator
    2.08
    ATED
    1.94
    ative
    1.86
    Act Density 0.119%

    No Known Activations