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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "any" and similar variations indicating quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     faſt
    -0.81
     Theſe
    -0.77
     houſe
    -0.76
     Coronel
    -0.72
     Cataluña
    -0.71
     Monfieur
    -0.71
    lıyor
    -0.70
     pleaſure
    -0.69
     itſelf
    -0.69
     Plutarch
    -0.68
    POSITIVE LOGITS
     no
    1.11
     none
    1.10
     any
    1.09
    none
    0.93
     other
    0.91
     nenhum
    0.85
     Any
    0.85
     никаких
    0.84
     some
    0.84
    principalTable
    0.84
    Act Density 0.118%

    No Known Activations