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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate personal identity and belonging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    URLException
    -0.82
    WebControls
    -0.68
    PRNewswire
    -0.62
    Xna
    -0.62
    horabuena
    -0.61
     BoxDecoration
    -0.60
    
    -0.60
    BrowserModule
    -0.60
    Hochspringen
    -0.59
     EconPapers
    -0.59
    POSITIVE LOGITS
     "¿
    0.63
     proverbs
    0.59
     getResources
    0.58
     tubeless
    0.57
     gramm
    0.57
     “¿
    0.57
    ſelves
    0.56
    ſelf
    0.54
     Kup
    0.54
    makeConstraints
    0.53
    Act Density 0.427%

    No Known Activations