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

    Neuronpedia

    INDEX
    Explanations

    references to assistants in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unn
    -0.54
    StoryboardSegue
    -0.53
     airplane
    -0.52
    TURE
    -0.52
     lifetime
    -0.52
    bill
    -0.51
     kurtka
    -0.51
    bravo
    -0.51
    MessageTagHelper
    -0.51
     Projection
    -0.50
    POSITIVE LOGITS
    WriteTagHelper
    0.45
     aint
    0.41
     wont
    0.40
     dreapta
    0.39
     AttributeError
    0.39
    angliski
    0.38
     stanga
    0.37
    RETURNS
    0.36
    findpost
    0.36
    Décès
    0.33
    Act Density 0.312%

    No Known Activations