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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating influence or impact on individuals or circumstances

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

    any followed by qualifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.66
     utafitiHapana
    -0.57
    principalColumn
    -0.56
     שוליים
    -0.53
    versiti
    -0.52
     ujednoznacz
    -0.50
     հղումներ
    -0.47
    <0x88>
    -0.47
    CloseOperation
    -0.47
    Gön
    -0.47
    POSITIVE LOGITS
     quelconque
    0.63
     quelcon
    0.47
     żad
    0.46
     herhangi
    0.44
     any
    0.43
    有任何
    0.42
     alguno
    0.41
     whatsoever
    0.40
    kolwiek
    0.40
    Any
    0.39
    Act Density 0.582%

    No Known Activations