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

    Neuronpedia

    INDEX
    Explanations

    phrases related to uniqueness and unusual characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Equivalent
    -0.57
     SafeMath
    -0.54
     endometri
    -0.53
    цездатний
    -0.53
    CopyWith
    -0.52
    AddTagHelper
    -0.52
     pecho
    -0.51
     fotografico
    -0.49
     verifique
    -0.48
     vectorielle
    -0.47
    POSITIVE LOGITS
     unusual
    1.18
     Unusual
    1.14
    unusual
    1.11
     unique
    1.09
    Unusual
    1.07
     unconventional
    1.04
     uniqueness
    1.02
    unique
    0.96
     Unique
    0.93
     unik
    0.92
    Act Density 0.415%

    No Known Activations