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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparison and assessment of various levels or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    httphttps
    -0.52
    LElement
    -0.47
     preſent
    -0.46
     pleaſure
    -0.46
    ſelf
    -0.45
    UnsafeEnabled
    -0.45
    UnitTesting
    -0.44
     AppBar
    -0.44
     auffi
    -0.44
     Houſe
    -0.42
    POSITIVE LOGITS
     than
    3.91
    than
    2.53
     niż
    2.50
     THAN
    2.48
    Than
    2.44
     Than
    2.09
    THAN
    2.02
     än
    1.93
     než
    1.93
     kuin
    1.91
    Act Density 0.971%

    No Known Activations