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

    Neuronpedia

    INDEX
    Explanations

    sentence starters

    oai_token-act-pair · gpt-3.5-turbo

    common introductory phrases or transition words in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     alike
    -0.67
    ":[
    -0.62
    ucket
    -0.60
    imposed
    -0.59
    itud
    -0.58
    wrapper
    -0.57
     Erie
    -0.56
    aukee
    -0.56
     ¶
    -0.55
    ea
    -0.55
    POSITIVE LOGITS
    edes
    0.80
    resy
    0.76
    reditary
    0.73
    cknowled
    0.68
    letes
    0.66
    ructose
    0.65
    ixel
    0.64
    olon
    0.64
     Kap
    0.61
     Patton
    0.60
    Act Density 0.186%

    No Known Activations