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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a previous name or designation of an entity

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

    formerly: previous names/roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     вікісторінку
    -0.65
     pleaſure
    -0.62
     ApJ
    -0.57
    CDCl
    -0.53
     McQueen
    -0.53
    Sheet
    -0.52
    Rib
    -0.52
    Qin
    -0.51
    Srin
    -0.51
    Yuki
    -0.50
    POSITIVE LOGITS
     formerly
    1.52
    formerly
    1.34
     Formerly
    1.30
    Formerly
    1.17
     vroeger
    0.76
     früher
    0.67
     former
    0.65
     autrefois
    0.62
    former
    0.61
    かつて
    0.60
    Act Density 0.003%

    No Known Activations