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

    Neuronpedia

    INDEX
    Explanations

    words related to technology and scientific terms

    oai_token-act-pair · gpt-3.5-turbo

    suffixes and roots of words that suggest various forms of action or description

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     confidence
    -0.67
     hem
    -0.67
     sher
    -0.65
     pity
    -0.65
     customary
    -0.64
     stiff
    -0.63
     doubtful
    -0.63
     mourning
    -0.63
     retri
    -0.62
     parity
    -0.62
    POSITIVE LOGITS
    idae
    1.06
    Sys
    0.99
    aceae
    0.93
    Soft
    0.89
    Ops
    0.88
    Builder
    0.88
    gex
    0.86
    Tech
    0.84
    Wiki
    0.84
    Plus
    0.82
    Act Density 0.271%

    No Known Activations