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

    Neuronpedia

    INDEX
    Explanations

    actions or steps in a process

    oai_token-act-pair · gpt-3.5-turbo

    processes and actions related to workflows and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    existent
    -0.70
     overheard
    -0.67
    atti
    -0.64
     lately
    -0.63
    paren
    -0.61
     thwarted
    -0.60
    idon
    -0.60
     disadvant
    -0.60
    Die
    -0.60
     underest
    -0.59
    POSITIVE LOGITS
     proceed
    1.12
     proceeded
    0.95
     resumes
    0.95
     resumed
    0.92
     begin
    0.91
     commence
    0.90
     recomm
    0.90
     revert
    0.89
     resume
    0.85
     begins
    0.83
    Act Density 0.359%

    No Known Activations