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

    Neuronpedia

    INDEX
    Explanations

    instances of verbs related to coding and development tasks

    oai_token-act-pair · gpt-3.5-turbo

    various gerunds and actions related to decision-making and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dt
    -0.64
    txt
    -0.63
    elin
    -0.63
    ãĥĩãĤ£
    -0.63
    letters
    -0.63
    ette
    -0.61
    payer
    -0.60
    OUND
    -0.60
    bn
    -0.59
    letter
    -0.59
    POSITIVE LOGITS
    agascar
    0.74
     oneself
    0.69
     contexts
    0.66
    isbury
    0.66
    isphere
    0.62
    tains
    0.61
    initions
    0.60
     metic
    0.60
    emetery
    0.60
    RAG
    0.60
    Act Density 0.126%

    No Known Activations