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

    Neuronpedia

    INDEX
    Explanations

    words related to announcements or declarations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    onga
    -1.06
    tein
    -1.00
    aylor
    -0.99
    onz
    -0.92
    iking
    -0.91
    vag
    -0.90
    opez
    -0.89
     saline
    -0.88
    obos
    -0.86
    asures
    -0.84
    POSITIVE LOGITS
     announces
    1.17
    eering
    1.02
     announcements
    0.99
     announcing
    0.98
    daq
    0.97
     goodbye
    0.97
    ctl
    0.94
    doms
    0.94
     announced
    0.90
     proclaim
    0.90
    Act Density 0.911%

    No Known Activations