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

    Neuronpedia

    INDEX
    Explanations

    keywords related to programming and technical specifications

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and functions related to programming and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     indeed
    -0.51
    ogether
    -0.49
    emonium
    -0.45
     nonetheless
    -0.40
     simply
    -0.40
    redibly
    -0.40
     exactly
    -0.39
    .—
    -0.39
    ificantly
    -0.39
     definitively
    -0.38
    POSITIVE LOGITS
     fibre
    0.37
     caste
    0.37
    adish
    0.36
     humid
    0.35
     spice
    0.35
     tel
    0.33
    proc
    0.32
    stem
    0.32
     chipset
    0.32
    grain
    0.32
    Act Density 1.498%

    No Known Activations