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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Meksiku
    -0.95
    Personendaten
    -0.83
    хьтан
    -0.83
     betweenstory
    -0.81
    :✨
    -0.80
     ivelany
    -0.79
    Jeografia
    -0.79
    WriteBarrier
    -0.79
     invokingState
    -0.78
     therewith
    -0.78
    POSITIVE LOGITS
     hora
    0.54
     onOptions
    0.52
     Infórmanos
    0.51
    brano
    0.45
     were
    0.44
    BRANCH
    0.43
     sat
    0.43
     very
    0.43
    krati
    0.42
     meyd
    0.42
    Act Density 0.033%

    No Known Activations