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

    Neuronpedia

    INDEX
    Explanations

    verbs related to activities or tasks

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and present participles indicating ongoing actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reet
    -0.66
    lat
    -0.65
    heim
    -0.65
    cerning
    -0.62
     distinguishing
    -0.62
    nton
    -0.61
    webkit
    -0.59
    lo
    -0.57
    hester
    -0.57
    bal
    -0.57
    POSITIVE LOGITS
    irection
    0.73
    ependent
    0.70
    oaded
    0.66
     illegally
    0.66
     broke
    0.65
    ļé
    0.63
    oresc
    0.63
    entary
    0.62
     starve
    0.62
    GGGGGGGG
    0.61
    Act Density 0.284%

    No Known Activations