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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal and medical processes

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

    incorrectly or improperly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     savour
    -0.50
    humour
    -0.50
     meestal
    -0.49
     GetUser
    -0.46
     suele
    -0.46
     colourful
    -0.45
     brukar
    -0.45
     localised
    -0.45
    嘿嘿
    -0.45
     favourite
    -0.45
    POSITIVE LOGITS
     supuestamente
    0.69
     supposedly
    0.65
     incorrectly
    0.60
    providedIn
    0.57
    🤬
    0.57
     improperly
    0.56
    😡
    0.55
     allegedly
    0.54
     🤦
    0.54
     illegally
    0.53
    Act Density 0.099%

    No Known Activations