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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "retreat" and its variations

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

    retreat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Edison
    -0.56
    Edison
    -0.55
     Sonny
    -0.53
    Johns
    -0.53
    Parcelize
    -0.52
     Hasbro
    -0.50
     ionizing
    -0.50
     Buster
    -0.49
     Johns
    -0.49
     Manson
    -0.48
    POSITIVE LOGITS
     retreat
    2.05
     Retreat
    1.97
     retreats
    1.77
     retreated
    1.41
     retreating
    1.35
     retraite
    0.99
     retiro
    0.91
    ret
    0.83
     RET
    0.78
     retrait
    0.78
    Act Density 0.002%

    No Known Activations