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

    Neuronpedia

    INDEX
    Explanations

    negative or undesirable concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.76
    Datuak
    -0.67
    verständlich
    -0.60
    LabelTagHelper
    -0.58
    IRUS
    -0.57
    nodoc
    -0.56
     Kidd
    -0.55
    othesis
    -0.55
    ppets
    -0.55
    AndEndTag
    -0.54
    POSITIVE LOGITS
    èdia
    0.65
    faker
    0.59
    ={`/
    0.57
     hår
    0.57
     Signalez
    0.57
     yeter
    0.56
     Италијани
    0.53
     المعيارى
    0.53
    待
    0.51
    ’-
    0.51
    Act Density 0.237%

    No Known Activations