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

    Neuronpedia

    INDEX
    Explanations

    terms related to the safeguarding and rights of individuals, particularly vulnerable groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onden
    -0.15
    hood
    -0.15
    ê
    -0.14
    uminum
    -0.14
    postalcode
    -0.14
    strand
    -0.14
    ega
    -0.14
    erer
    -0.14
    ossible
    -0.13
    strict
    -0.13
    POSITIVE LOGITS
     against
    0.20
     Ade
    0.16
    ively
    0.16
    ably
    0.16
    /rest
    0.16
     Against
    0.15
    against
    0.15
     us
    0.14
    avian
    0.14
    ç¯Ħ
    0.14
    Act Density 0.065%

    No Known Activations