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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions of removal or eradication

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "take out"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esa
    -0.76
    inski
    -0.72
    isma
    -0.68
    ndra
    -0.68
    ioned
    -0.68
    ĸļ
    -0.67
    NG
    -0.67
    gnu
    -0.66
    BILITY
    -0.65
    ogue
    -0.64
    POSITIVE LOGITS
    stretched
    0.77
    fitted
    0.75
    doors
    0.75
    tan
    0.66
     levers
    0.66
     weeds
    0.63
    ãĥīãĥ©
    0.63
    ta
    0.62
    taker
    0.62
     swat
    0.61
    Act Density 0.032%

    No Known Activations