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

    Neuronpedia

    INDEX
    Explanations

    the word "First" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apper
    -0.15
    swick
    -0.15
    odd
    -0.15
    otate
    -0.14
    asm
    -0.14
    ständ
    -0.14
    ItemSelected
    -0.13
     Tutor
    -0.13
    ilk
    -0.13
    بÙĪ
    -0.13
    POSITIVE LOGITS
    enberg
    0.22
     First
    0.17
     Amendment
    0.16
     Aid
    0.16
    ynes
    0.16
     Nations
    0.16
    Bank
    0.16
    eba
    0.15
     responder
    0.15
    ENER
    0.15
    Act Density 0.044%

    No Known Activations