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

    Neuronpedia

    INDEX
    Explanations

    references to decision-making processes and options related to goals and outcomes

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

    Follows comma or parenthesis, followed by "then"

    np_acts-logits-general · gemini-2.0-flash

    then after comma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Exacts
    -0.67
     Lordships
    -0.59
    конец
    -0.58
    ことができました
    -0.54
     Infórmanos
    -0.51
    if
    -0.51
    enumii
    -0.49
    fromnode
    -0.49
    dAtA
    -0.48
    iastes
    -0.48
    POSITIVE LOGITS
     then
    3.40
    then
    2.48
     entonces
    2.37
     allora
    2.31
     Then
    2.28
    Then
    2.24
     THEN
    2.06
     então
    2.04
     dann
    1.96
     alors
    1.93
    Act Density 0.700%

    No Known Activations