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

    Neuronpedia

    INDEX
    Explanations

    words associated with societal issues and policies

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to societal challenges and responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aneously
    -0.76
    leases
    -0.68
    ALLY
    -0.68
    Status
    -0.67
    spell
    -0.63
    planes
    -0.63
    duty
    -0.62
    dry
    -0.61
    roximately
    -0.60
    plane
    -0.60
    POSITIVE LOGITS
    pace
    1.03
    etting
    1.01
    cape
    1.01
     inherent
    0.99
    pring
    0.96
     outlined
    0.94
    etter
    0.93
     plag
    0.91
    omen
    0.90
    cale
    0.88
    Act Density 0.274%

    No Known Activations