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

    Neuronpedia

    INDEX
    Explanations

    references to being part of a group or collective

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Romains
    -0.52
     enfans
    -0.50
    wife
    -0.50
     Holanda
    -0.48
    parts
    -0.48
     Grecs
    -0.46
     désert
    -0.46
     Haare
    -0.45
     Accesorios
    -0.45
     repair
    -0.43
    POSITIVE LOGITS
     nahilalakip
    0.82
    PyExc
    0.63
    endcsname
    0.58
    extAlignment
    0.58
     виправивши
    0.57
    migrationBuilder
    0.57
     EconPapers
    0.55
    ArrowToggle
    0.53
     Мексичка
    0.53
     autorytatywna
    0.52
    Act Density 0.233%

    No Known Activations