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

    Neuronpedia

    INDEX
    Explanations

    phrases comparing two different elements using the term 'as'

    oai_token-act-pair · gpt-3.5-turbo

    comparisons or similes expressed with the word "as."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DIT
    -0.74
    姫
    -0.71
    åĪ
    -0.67
    GES
    -0.62
    ASE
    -0.61
    SHIP
    -0.59
    Firstly
    -0.59
     Classes
    -0.58
     decrease
    -0.58
    ries
    -0.58
    POSITIVE LOGITS
    pired
    1.21
    bestos
    0.99
    phalt
    0.95
    par
    0.94
    ylum
    0.94
    phy
    0.92
    piring
    0.91
    pir
    0.90
    pires
    0.89
     usual
    0.87
    Act Density 0.069%

    No Known Activations