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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "through"

    oai_token-act-pair · gpt-3.5-turbo

    the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pi
    -0.72
    witch
    -0.72
    tle
    -0.70
    oka
    -0.70
     Temper
    -0.70
    CVE
    -0.69
    ty
    -0.66
    thood
    -0.65
    gage
    -0.64
    intosh
    -0.64
    POSITIVE LOGITS
     midst
    1.00
     process
    0.98
     backdoor
    0.98
     entirety
    0.97
     maze
    0.96
     labyrinth
    0.95
     prism
    0.94
     doorway
    0.92
     veins
    0.90
     confines
    0.88
    Act Density 0.142%

    No Known Activations