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

    Neuronpedia

    INDEX
    Explanations

    phrases related to commenting on individual cases and policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EEDED
    -0.15
    issan
    -0.14
    entai
    -0.14
    orton
    -0.14
    aptop
    -0.13
    λοι
    -0.13
     interes
    -0.13
    ãĥ¼ãĥ¼
    -0.13
    inic
    -0.12
    Âį
    -0.12
    POSITIVE LOGITS
     specific
    0.40
     specifics
    0.38
    specific
    0.32
     individual
    0.32
    -specific
    0.31
     especÃŃf
    0.31
    åħ·ä½ĵ
    0.30
     Specific
    0.29
    Specific
    0.28
     ongoing
    0.26
    Act Density 0.056%

    No Known Activations