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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and references to specific locations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Atomic
    -0.17
    ær
    -0.16
    ì²ľ
    -0.15
    ystone
    -0.15
     surv
    -0.14
    cheon
    -0.14
    argent
    -0.14
     бÑĥдÑĥÑī
    -0.14
    leton
    -0.14
     survival
    -0.13
    POSITIVE LOGITS
     enemy
    0.21
    odon
    0.16
     DPR
    0.16
     ceasefire
    0.15
    /chart
    0.15
    .cum
    0.15
     Shel
    0.15
    enemy
    0.15
    positions
    0.14
    pts
    0.14
    Act Density 0.008%

    No Known Activations