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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating negative states or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     externi
    -0.37
    BeginInit
    -0.34
    Kanpo
    -0.33
    テー
    -0.32
    iam
    -0.30
    FXML
    -0.30
    vel
    -0.29
    TestTools
    -0.29
     pulled
    -0.29
     دیکھیے
    -0.29
    POSITIVE LOGITS
     nowhere
    1.00
     bounds
    0.89
     sight
    0.86
     whack
    0.83
     sync
    0.82
     reach
    0.75
     Bounds
    0.71
     harms
    0.71
     pocket
    0.69
     synch
    0.68
    Act Density 0.193%

    No Known Activations