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

    Neuronpedia

    INDEX
    Explanations

    references to tigers and their habitats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tridge
    -0.16
    letcher
    -0.16
    ategory
    -0.15
    YTE
    -0.15
    abilit
    -0.15
    ibold
    -0.15
    xea
    -0.14
    Responder
    -0.14
     Hodg
    -0.14
    tes
    -0.14
    POSITIVE LOGITS
     Woods
    0.30
     cub
    0.25
     Tiger
    0.22
     Cub
    0.22
     Cubs
    0.21
     Claw
    0.21
     woods
    0.20
     claw
    0.20
     tiger
    0.18
     Lily
    0.18
    Act Density 0.008%

    No Known Activations