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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the term "connect" in programming contexts

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

    connect to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inv
    -0.34
     st
    -0.31
     Hyman
    -0.31
    rowData
    -0.30
     Aub
    -0.30
     ob
    -0.30
    ❃
    -0.29
     Sturm
    -0.29
    ulkner
    -0.29
     ab
    -0.29
    POSITIVE LOGITS
    connect
    3.19
    Connect
    2.41
     Connect
    2.23
     connect
    2.19
    CONNECT
    1.98
     CONNECT
    1.81
    connects
    1.69
     connects
    1.62
    connecting
    1.47
     connecting
    1.45
    Act Density 0.003%

    No Known Activations