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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs ending in 'ed'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "done" followed by various contexts of completion or finality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lar
    -0.76
    ulates
    -0.74
    olson
    -0.72
    liner
    -0.71
    imov
    -0.71
    dayName
    -0.71
    Reviewer
    -0.70
    ussen
    -0.69
    lights
    -0.69
    uyomi
    -0.68
    POSITIVE LOGITS
    pez
    1.04
     nothing
    0.74
     away
    0.71
     differently
    0.67
     prepar
    0.66
     done
    0.65
     condu
    0.65
    ggie
    0.63
     administr
    0.63
    xxxxxxxx
    0.63
    Act Density 0.026%

    No Known Activations