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

    Neuronpedia

    INDEX
    Explanations

    the presence of certain tags or markers in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    новништво
    -0.89
    ^(@)
    -0.70
     isInitialized
    -0.70
    enschappelijke
    -0.67
    EndInit
    -0.66
    %");
    -0.66
     = 
    -0.63
    Hozzáférés
    -0.62
    /−
    -0.62
     Савезне
    -0.61
    POSITIVE LOGITS
     című
    0.67
     starring
    0.66
     released
    0.58
    which
    0.55
     remake
    0.55
     featuring
    0.53
     Part
    0.53
     premiered
    0.51
     (
    0.49
     aired
    0.49
    Act Density 0.153%

    No Known Activations