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

    Neuronpedia

    INDEX
    Explanations

    mentions of arguments in programming contexts

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

    argument

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    protoimpl
    -0.44
    蚪
    -0.44
    oredCriteria
    -0.40
     Oto
    -0.40
    艋
    -0.39
     Lana
    -0.38
    -0.37
     Wes
    -0.36
    MAO
    -0.36
     ProtoMessage
    -0.36
    POSITIVE LOGITS
     argument
    1.98
    argument
    1.90
     Argument
    1.77
     arguments
    1.70
     ARGUMENT
    1.66
    Argument
    1.66
     Arguments
    1.55
    arguments
    1.54
     argumento
    1.53
     argue
    1.51
    Act Density 0.008%

    No Known Activations