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

    Neuronpedia

    INDEX
    Explanations

    locations or places

    oai_token-act-pair · gpt-3.5-turbo

    terms referring to geographical locations or designators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    child
    -0.81
    PDATE
    -0.72
    staking
    -0.71
    manship
    -0.69
    geon
    -0.67
    ħĭ
    -0.64
     Rollins
    -0.64
     Duchess
    -0.64
    dress
    -0.63
     Springs
    -0.61
    POSITIVE LOGITS
    ator
    1.29
    ational
    1.26
    abulary
    1.21
    ations
    1.20
    ators
    1.13
    atell
    1.12
    utor
    1.09
    ution
    1.09
    uments
    1.05
    ality
    1.04
    Act Density 0.031%

    No Known Activations