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

    Neuronpedia

    INDEX
    Explanations

    instances of being trapped or caught in various situations

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

    caught or trapped

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.57
     nakalista
    -0.53
    complexContent
    -0.51
     nahilalakip
    -0.50
     Infórmanos
    -0.49
     surla
    -0.49
     للمعارف
    -0.49
    новниш
    -0.49
    SpringRunner
    -0.47
     $__
    -0.47
    POSITIVE LOGITS
     stuck
    0.56
     trapped
    0.56
     Flucht
    0.54
    Lost
    0.52
    stuck
    0.46
    escaped
    0.46
    Escape
    0.46
    ESCAPE
    0.46
    escape
    0.45
     caught
    0.45
    Act Density 0.014%

    No Known Activations