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

    Neuronpedia

    INDEX
    Explanations

    words related to physical positioning or placement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.67
    parsedMessage
    -0.64
     miniaturka
    -0.56
     coroa
    -0.56
     senhora
    -0.52
     propOrder
    -0.51
     liderança
    -0.50
     Substanz
    -0.49
     personalidade
    -0.49
     jouet
    -0.49
    POSITIVE LOGITS
    ping
    0.76
    rem
    0.65
     rem
    0.64
     ping
    0.63
     lying
    0.59
    一
    0.56
     lay
    0.56
    Ping
    0.56
     imp
    0.54
     kits
    0.54
    Act Density 0.208%

    No Known Activations