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

    Neuronpedia

    INDEX
    Explanations

    phrases related to negative emotions or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     onCreateView
    -0.43
     members
    -0.43
    úsqueda
    -0.43
    bayan
    -0.42
     an
    -0.42
     while
    -0.42
     Kennedy
    -0.41
     server
    -0.41
     ‘
    -0.41
    sterdam
    -0.40
    POSITIVE LOGITS
    Geplaatst
    0.71
     Theſe
    0.70
    0.70
     Reſ
    0.68
     Efq
    0.64
     disagre
    0.64
     Anſ
    0.64
    Hochspringen
    0.61
     arşivlendi
    0.60
    TypedDataSet
    0.60
    Act Density 0.582%

    No Known Activations