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

    Neuronpedia

    INDEX
    Explanations

    references to specific metrics or comparisons in technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    findpost
    -1.01
    Hochspringen
    -0.87
    UserScript
    -0.86
    MLLoader
    -0.83
    gameserver
    -0.81
    клопе
    -0.80
    contentLoaded
    -0.79
     ainfi
    -0.77
    Spoljašnje
    -0.77
     RIPRODUZIONE
    -0.74
    POSITIVE LOGITS
     I
    0.55
    …
    0.52
    ,
    0.50
    .
    0.49
     K
    0.47
     his
    0.47
     O
    0.47
     F
    0.46
     –
    0.46
     Don
    0.45
    Act Density 0.545%

    No Known Activations