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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and conversational cues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ynes
    -0.14
    odd
    -0.13
    anko
    -0.13
    Odd
    -0.13
    _legacy
    -0.12
    agan
    -0.12
     verde
    -0.12
    лива
    -0.12
     autorelease
    -0.12
     Odd
    -0.12
    POSITIVE LOGITS
     Interview
    0.23
     interviewer
    0.22
     Yeah
    0.22
     interview
    0.21
    Interview
    0.20
     yeah
    0.20
     entrev
    0.19
     narr
    0.19
     narrator
    0.19
    Yeah
    0.18
    Act Density 0.108%

    No Known Activations