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

    Neuronpedia

    INDEX
    Explanations

    words related to size, comparing objects as big or small

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and words that express relationships between large and small entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dstg
    -0.83
    webkit
    -0.76
    iPhone
    -0.66
    911
    -0.66
     Horde
    -0.66
     Incident
    -0.65
    steel
    -0.64
    throp
    -0.63
    iston
    -0.63
     Cipher
    -0.62
    POSITIVE LOGITS
     sqor
    0.90
     Medina
    0.84
     females
    0.69
     valleys
    0.68
     sellers
    0.67
     sink
    0.66
     seller
    0.66
     Nebula
    0.66
     lows
    0.65
    DVD
    0.65
    Act Density 0.433%

    No Known Activations