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

    Neuronpedia

    INDEX
    Explanations

    superlatives and comparative phrases

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    starter
    -0.76
    vertisement
    -0.70
    amera
    -0.69
    mbuds
    -0.67
    hovah
    -0.67
    syn
    -0.67
    zik
    -0.67
    phis
    -0.66
    rogram
    -0.66
    SEA
    -0.65
    POSITIVE LOGITS
     imaginable
    1.36
     conceivable
    1.15
     possible
    0.99
     practicable
    0.80
     part
    0.79
     aspects
    0.78
     minds
    0.77
     parts
    0.77
     twist
    0.77
     flavours
    0.76
    Act Density 0.104%

    No Known Activations