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

    Neuronpedia

    INDEX
    Explanations

    phrases and words related to language and communication

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of words and their significance in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roxy
    -0.74
    noon
    -0.72
    romeda
    -0.72
    Offline
    -0.69
     MFT
    -0.69
    cffff
    -0.68
    ramid
    -0.66
     srfAttach
    -0.66
    ONSORED
    -0.62
     Skydragon
    -0.62
    POSITIVE LOGITS
    mith
    1.69
     uttered
    1.45
     spoken
    1.32
     describing
    1.06
     coined
    1.00
     typed
    0.95
     aloud
    0.94
    pell
    0.93
     phrases
    0.92
    writers
    0.89
    Act Density 0.123%

    No Known Activations