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

    Neuronpedia

    INDEX
    Explanations

    phrases related to mechanical and structural components

    oai_token-act-pair · gpt-3.5-turbo

    suffixes or root words related to various objects and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    paren
    -0.80
    ENN
    -0.77
    İĭ
    -0.77
    paces
    -0.76
    vez
    -0.75
    ãĥĹ
    -0.74
    soDeliveryDate
    -0.74
    Ô
    -0.72
    kus
    -0.70
    know
    -0.70
    POSITIVE LOGITS
     ridden
    0.87
     generator
    0.86
    ishly
    0.85
     clad
    0.84
     gland
    0.82
     canopy
    0.82
     operator
    0.81
     rendition
    0.80
     ridge
    0.80
     liner
    0.78
    Act Density 0.481%

    No Known Activations