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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "doing" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    doing + ongoing action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     transparencia
    -0.59
    <bos>
    -0.58
     ſche
    -0.56
     houſe
    -0.53
     ſtate
    -0.52
     transparan
    -0.52
    AdapterView
    -0.50
     ſon
    -0.50
    ähteet
    -0.49
     ſch
    -0.47
    POSITIVE LOGITS
    doing
    1.57
     Doing
    1.48
    Doing
    1.47
     doing
    1.37
     DOING
    1.33
     doin
    1.05
     doings
    0.83
    ing
    0.75
     Performing
    0.73
    conducting
    0.73
    Act Density 0.010%

    No Known Activations