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

    Neuronpedia

    INDEX
    Explanations

    references to plural forms and shared responsibilities within a community or group context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     understatement
    -0.52
    atrième
    -0.50
     >=",
    -0.49
    很简单
    -0.48
    rition
    -0.47
     delas
    -0.46
     Salam
    -0.46
     salam
    -0.46
     Jor
    -0.45
    :"-"`
    -0.45
    POSITIVE LOGITS
    AndEndTag
    0.98
     AssemblyCulture
    0.83
    Hentet
    0.67
    Referencer
    0.63
     equally
    0.62
    gameserver
    0.58
     nakalista
    0.55
    angliski
    0.51
     EconPapers
    0.51
    hObject
    0.51
    Act Density 0.494%

    No Known Activations