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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "dear" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gers
    -0.17
    gear
    -0.17
    edu
    -0.16
    ella
    -0.16
    ucz
    -0.16
    gnore
    -0.15
    vet
    -0.15
    errat
    -0.15
    oodle
    -0.15
    orsk
    -0.15
    POSITIVE LOGITS
     diary
    0.21
     Diary
    0.21
    born
    0.20
     departed
    0.18
     lord
    0.18
    liest
    0.17
     Sir
    0.17
     sir
    0.17
    ths
    0.17
    íŀĪ
    0.16
    Act Density 0.010%

    No Known Activations