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

    Neuronpedia

    INDEX
    Explanations

    phrases related to carrying out actions or tasks

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to performing actions or carrying out tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esa
    -0.76
    lua
    -0.76
    oxin
    -0.65
    enty
    -0.64
     Soup
    -0.64
    username
    -0.62
    onian
    -0.62
    isma
    -0.61
    edia
    -0.61
    focus
    -0.60
    POSITIVE LOGITS
    uate
    0.85
     duties
    0.82
     tasks
    0.80
     executions
    0.80
     renovations
    0.79
     reconnaissance
    0.78
     abortions
    0.78
     repairs
    0.77
     surveillance
    0.74
     killings
    0.74
    Act Density 0.047%

    No Known Activations