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

    Neuronpedia

    INDEX
    Explanations

    terms related to the protection of rights and welfare

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SED
    -0.19
     onBackPressed
    -0.15
    stract
    -0.15
    oppins
    -0.15
    licable
    -0.15
    ylland
    -0.15
    antry
    -0.15
    itra
    -0.15
    ais
    -0.15
    istrat
    -0.14
    POSITIVE LOGITS
    ively
    0.34
     against
    0.28
    ive
    0.28
    iveness
    0.26
    ors
    0.25
     Against
    0.24
    Against
    0.21
    against
    0.21
    IVE
    0.20
    orsk
    0.18
    Act Density 0.030%

    No Known Activations