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

    Neuronpedia

    INDEX
    Explanations

    instances of the word 'you' and its variations, indicating a focus on direct address and conversational tone

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isci
    -0.18
    -caret
    -0.15
     ç©
    -0.15
    okud
    -0.15
    memberOf
    -0.14
    overnment
    -0.14
    tery
    -0.14
    ifton
    -0.14
    Neal
    -0.14
    razier
    -0.14
    POSITIVE LOGITS
    'll
    0.28
     may
    0.24
     happen
    0.23
     might
    0.22
    've
    0.21
    're
    0.19
    'd
    0.19
     possibly
    0.19
     ought
    0.19
     could
    0.19
    Act Density 0.019%

    No Known Activations