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

    Neuronpedia

    INDEX
    Explanations

    phrases related to depletion or exhaustion

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

    running out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.45
    tanleria
    -0.45
    ulaski
    -0.40
    Groetjes
    -0.38
    //
    -0.37
     McGraw
    -0.37
     aufgebaut
    -0.36
     discovery
    -0.35
     avven
    -0.35
     Pulaski
    -0.35
    POSITIVE LOGITS
     exhausted
    0.64
     Exhaus
    0.56
     épu
    0.54
    หมด
    0.52
    يكب
    0.52
     depleted
    0.51
    exhaus
    0.51
     deple
    0.50
     kaarangay
    0.49
    exhaust
    0.48
    Act Density 0.071%

    No Known Activations