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

    Neuronpedia

    INDEX
    Explanations

    expressions related to saying or communicating something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    quotes or phrases that contain the word "something" followed by supporting commentary

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Grail
    -0.70
    ipation
    -0.69
    ibal
    -0.67
    ouple
    -0.67
     Folder
    -0.66
    SEA
    -0.65
    hire
    -0.64
     patronage
    -0.64
     Cruiser
    -0.63
     Geh
    -0.61
    POSITIVE LOGITS
     aloud
    1.43
     loudly
    1.36
     louder
    1.15
     loud
    1.09
     publicly
    1.03
     verbally
    0.98
     uttered
    0.95
     sarcast
    0.93
     anonymously
    0.91
     orally
    0.89
    Act Density 0.161%

    No Known Activations