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

    Neuronpedia

    INDEX
    Explanations

    quotes and excerpts from interviews with people

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to interviews and communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Mods
    -0.70
     disliked
    -0.68
    edia
    -0.61
    Tags
    -0.61
    Pub
    -0.60
    itures
    -0.57
     aven
    -0.57
    usercontent
    -0.57
     reven
    -0.55
    fuck
    -0.54
    POSITIVE LOGITS
     interviewer
    0.95
     interview
    0.93
     translator
    0.90
     telephone
    0.90
     phone
    0.85
    EStream
    0.83
     understatement
    0.82
     interpreter
    0.82
     applause
    0.82
     interviewed
    0.81
    Act Density 0.154%

    No Known Activations