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

    Neuronpedia

    INDEX
    Explanations

    phrases related to news sources or specific publications

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    wagen
    -0.69
     Mata
    -0.65
    hire
    -0.64
    aneously
    -0.64
     caste
    -0.63
    venge
    -0.63
    oldemort
    -0.62
     erection
    -0.62
    gie
    -0.61
    loader
    -0.61
    POSITIVE LOGITS
    NPR
    1.12
     NPR
    0.99
     Transcript
    0.89
    DEF
    0.82
    nw
    0.80
     transcripts
    0.79
    OST
    0.78
    TIT
    0.77
     Radio
    0.76
     podcasts
    0.74
    Act Density 0.006%

    No Known Activations