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

    Neuronpedia

    INDEX
    Explanations

    verbs related to physical actions

    oai_token-act-pair · gpt-3.5-turbo

    comma-separated lists or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quished
    -0.78
    sted
    -0.72
    ¬¼
    -0.69
    ãĤ¦ãĤ¹
    -0.69
    é¾
    -0.64
    awed
    -0.63
    Initialized
    -0.60
    prises
    -0.59
    abouts
    -0.59
    GGGGGGGG
    -0.58
    POSITIVE LOGITS
     educate
    1.26
     organize
    1.24
     improve
    1.23
     eliminate
    1.23
     modify
    1.22
     stabilize
    1.21
     reduce
    1.21
     create
    1.20
     simplify
    1.19
     formulate
    1.19
    Act Density 0.294%

    No Known Activations